Today we release our first self-hosted Auphonic Speech Recognition Engine using the open-source Whisper model by OpenAI!
With Whisper, you can now integrate automatic speech recognition in 99 languages into your Auphonic audio post-production workflow, without creating an external account and without extra costs!

Whisper Speech Recognition in Auphonic

So far, Auphonic users had to choose one of our integrated external service providers (Wit.ai, Google Cloud Speech, Amazon Transcribe, Speechmatics) for speech recognition, so audio files were transferred to an external server, using external computing powers, that users had to pay for in their external accounts.

The new Auphonic Speech Recognition is using Whisper, which was published by OpenAI as an open-source project. Open-source means, the publicly shared GitHub repository contains a complete Whisper package including source code, examples, and research results.
However, automatic speech recognition is a very time and hardware-consuming process, that can be incredibly slow using a standard home computer without special GPUs. So we decided to integrate this service and offer you automatic speech recognition (ASR) by Whisper processed on our own hardware, just like any other Auphonic processing task, giving you quite some benefits:

• No external account is needed anymore to run ASR in Auphonic.
• Your data doesn't leave our Auphonic servers for ASR processing.
• No extra costs for external ASR services.
• Additional Auphonic pre- and post-processing for more accurate ASR, especially for Multitrack Productions.
• The quality of Whisper ASR is absolutely comparable to the “best” services in our comparison table.

How to use Whisper?

To use the Auphonic Whisper integration, you just have to create a production or preset as you are used to and select “Auphonic Whisper ASR” as “Service” in the section Speech Recognition.
This option will automatically appear for Beta and paying users. If you are a free user but want to try Whisper: please just ask for access!

When your Auphonic speech recognition is done, you can download your transcript in different formats and may edit or share your transcript with the Auphonic Transcript Editor.
For more details about all our integrated speech recognition services, please visit our Speech Recognition Help and watch this channel for Whisper updates – soon to come.

Why Beta?

We decided to launch Whisper for Beta and paying users only, as Whisper was just published end of September and there was not enough time to test every single use case sufficiently.
Another issue is the required computing power: for suitable scaling of the GPU infrastructure, we need a beta phase to test the service while we are monitoring the hardware usage, to make sure there are no server overloads.

Conclusion

Automatic speech recognition services are evolving very quickly, and we've seen major improvements over the past few years.
With Whisper, we can now perform speech recognition without extra costs on our own GPU hardware, no external services are required anymore.

Auphonic Whisper ASR is available for Beta and paying users now, free users can ask for Beta access.
You are very welcome to send us feedback (directly in the production interface or via email), whether you notice something that works particularly well or discover any problems.
Your feedback is a great help to improve the system!

In addition to our Leveler, Denoiser, and Adaptive 'Hi-Pass' Filter, we now release the missing equalization feature with the new Auphonic AutoEQ.
The AutoEQ automatically analyzes and optimizes the frequency spectrum of a voice recording, to remove sibilance (De-esser) and to create a clear, warm, and pleasant sound - listen to the audio examples below to get an idea about what it does.

Screenshot of manually adjusted example settings for the equalizer plug-in 'Pro-Q3' by fabfilter.

What is Equalization and why is it difficult?

Equalization (EQ) in audio recording and reproduction is the process of adjusting the volume of different frequency bands within a signal.
The following vocal EQ cheat sheet, published by Producer Hive, will give you a small impression, of what can be influenced by equalizing:

Vocal EQ Cheat Sheet by Producer Hive.

On the other hand, it is very easy to ruin a good voice recording with manual heavy-handed equalization, resulting in voices, that sound very sharp or muddy or even like the speaker had a blocked nose.
Besides the skill and experience of an audio engineer, manual adjustments of frequencies also require a very good and linear studio playback device. For example, performing manual equalization with strongly bass-heavy speakers would most likely lead to a very sharp, unpleasant listening experience using treble-heavy headphones.

For singletrack productions with more than one speaker, equalizing is also a very complex and time-consuming process, as every voice has its unique frequency spectrum and needs its own equalization. One could separate speakers with cuts or create a track envelope to fade from one speaker to another, however, any solution is a very tedious job, if you do it by hand.

That is where the Auphonic AutoEQ comes in! All those steps are now available in just one click!

How does the Auphonic AutoEQ work?

The Auphonic Web Service analyzes your audio content and classifies the audio file into small and meaningful segments like music, silence, different speakers, etc. to process every single segment with the best matching algorithms.
All our features like the Adaptive Leveler, Dynamic Denoising, Adaptive 'Hi-Pass' Filtering, and now the new AutoEQ filter option are built on top of this basic processing.

Using Auphonic AutoEQ, spectral EQ profiles are created for each speaker separately and permanently changing over time. The aim of those time-dependent EQ profiles is to create a constant, pleasant sound in the output file even if there are slightly changing voices in the record, for example, due to modified speaker-microphone positions.

Audio Examples

Here are two short audio examples, which demonstrate some features of our AutoEQ.
We recommend listening with headphones so you can hear all the details.

Example 1. Female Speaker with Background Music

In the following example (BCB: The Voices of Bainbridge Island) of a female narrator speaking while background music is playing, you can easily recognize quite sharp 'sss' sounds in the female voice. This sharpness in the female voice is removed by the so-called De-essing feature of the Auphonic AutoEQ, while the background music is not changed.

Example 2. Dialog of Male and Female Speakers

The next example (BCB: The Voices of Bainbridge Island) shows how the AutoEQ optimizes a singletrack record containing two speakers with different voice characteristics. Our AutoEQ algorithms analyze each voice separately and calculate the matching frequency adjustments to optimize the voice of every single speaker.

AutoEQ Beta Integration in the Auphonic Web Service

To use the Auphonic AutoEQ, you just have to create a production or preset as you are used to, toggle “Advanced Parameters” on the top right in the section “Audio Algorithms” and select “Voice AutoEQ” within “Filtering”:

For a first test period, the AutoEQ will only be available for Beta and paying users, to incorporate your feedback and finalize an optimized version.
If you are a free user but want to try Auphonic AutoEQ: please just ask for access!

Practical Tips

For best results using Auphonic AutoEQ, however, it is still necessary, that your audio content is of sufficiently good quality, as no equalizer can make up frequencies that are not there in the first place. Audio files with low bitrates often lack important frequencies, that cannot be recovered by equalizing. AutoEQ is just a feature to boost or cut individual frequency bands, not a bandwidth extension. For more information about required audio quality, see the former blog post: Audio File Formats and Bitrates for Podcasts.

Another important topic is the definition of the 'best result'. Equalizing is a very subjective task, that differs a lot depending on every personal opinion. So Auphonic AutoEQ is set up to follow quite conservative rules of equalizing and rather apply subtle tweaks and remove obvious problems, than support personal preferences. This also means, your record will experience no significant changes from Auphonic AutoEQ if it sounds reasonably OK or pretty good already.

Conclusion

Auphonic audio post production algorithms keep getting better and better in leaps and bounds lately, offering you new Beta Features: Beta Auphonic Denoiser, Beta Auphonic Speech Recognition, and Beta Auphonic AutoEQ.
Right now we are fine-tuning all our current Beta Features with high intensity to release a new upgraded version of our Auphonic Web Service as soon as possible.
Please watch this channel for further updates – soon to come.

If you have any feedback for us or want to become a Beta user, you are very welcome to comment directly in our production interface or to contact us via email!

To start a new decade of automatic audio post production with Auphonic, we are happy to launch a few updates:

New Website Design

Opening the new homepage today, you might have noticed that our website looked different from what you had been used to before. Keeping our customers’ feedback from last year in mind, we designed a new vision for Auphonic.

Our new website features a refreshed look with an improved, more engaging, and functional user experience. Moreover, a more straightforward, intuitive, and accessible navigation will give you a seamless workflow and a comfortable exploration of Auphonic’s features.
We hope it will be easier to explore the diversity of applications that Auphonic has. In the end, however, as before, you will have the same full functionality of Auphonic available to you and some extra features if you are using our paid packages or subscriptions.

Take a look yourself: New Auphonic Landing Page

Free Access to our Advanced and Beta Algorithms

In the past, only paying Auphonic users had access to the advanced algorithm parameters, to multitrack advanced audio algorithms, and to our Dynamic Denoising and AutoEQ beta models.

We now enabled all advanced algorithms for free users, and you can use them for 2 hours of audio free each month!

Using the Dynamic Denoiser, you can define whether Auphonic should remove only static or also fast-changing noises and if we should keep or eliminate music. For even greater speech intelligibility control, it is possible to manually adjust the amount of denoising to strike the perfect balance between clarity and ambiance.

The AutoEQ automatically analyzes and optimizes the frequency spectrum of a voice recording to remove sibilance (De-Esser) and to create a clear, warm, and pleasant sound.
The equalization of multi-speaker audio can be complex and time-consuming, as each voice requires its own unique frequency spectrum equalization. Our AutoEQ simplifies this process by creating separate, time-dependent EQ profiles for each speaker, ensuring a consistent and pleasant sound output despite any changes in the voices during the recording.

Our advanced algorithm parameters help you to meet all common audio specifications of platforms like Netflix, Audible, podcasts, broadcasters (EBU R128, ATSC A/85, radio and mobile, commercials) in one click. You can define a set of target parameters (integrated loudness, true peak level, dialog normalization, MaxLRA, MaxM, MaxS), like -16 LUFS for podcasts, and we will produce the audio accordingly.
In addition, they offer more control for multitrack productions and for the Adaptive Leveler.

We would like to give away free hours for new Auphonic users, to try out our free advanced algorithms. Please use this URL to register your new Auphonic account. the code is valid till end of March 2023 and will give you 5 extra production hours for the next month. Happy content creation!

More Audio Examples

There is no better way to experience Auphonic than hearing the difference our post production tool makes when applied to different types of audio and content.
We are happy to share that our new features page now contains some new audio examples you can listen to explore our web tool, and we will add even more examples in the next weeks.

We've listened to your feedback and are excited to announce the introduction of metadata variables in Auphonic for more advanced use of our Basic and Extended Metadata.
This new feature allows you to use metadata fields from your input files to automate workflows. You can easily reference any field by using { curly brackets } and typing the field name, such as {title}, {artist}, {album}, {track}, and more.
To get started, take a look at our Formatting Examples and the Table of all Variables to see all the available options.

Whether you are using the Auphonic Web Service or our API, metadata variables can be applied whenever metadata values are set. They are particularly helpful when working with Presets, Batch Productions, or Watch Folders!

For instance, consider the left column of the following table as input ending up in the metadata as shown in the right column:

Note:
Please mind that fields can not refer to each other in cycles (e.g., if {title} refers to {album}, {album} may not refer to {title}). While the input form will not show any errors, the metadata will most likely not be correct and the production will generate a warning.

Formatting Examples

With metadata variables you can automatically generate your output file basename based on the input filename and podcast metadata, like album, track, and title.
If you have, for example, a podcast preset or input file with the album name "The Placeholder Podcast", you can automatically name your episode title like your input filename. By combining the metadata variables "album" name and your generated episode "title" with any text patterns, like "denoised" in this case, you can create your individual output file basename:

The next example shows how you can create truly unique output file basenames with timestamps. Here, a track number is, together with the input file basename, added up as episode title. So, your unique output file basename could be a combination of this generated episode title with the time and date, when your Auphonic production was started:

See example 3 for more time formatting examples, and this table for the full list of symbols that can be used for formatting dates.

The following time and date example outputs would be possible for a production created at 7:05 pm on Saturday, January 30th in 1999:

See this table for the full list of symbols that can be used for formatting dates.

For the list fields "tags", "chapters", "outputfiles", and multitrack "input_filename/basename", you need to reference every value separately by adding .N to your variable – Where N stands for ascending ordinal numbers starting from 0.
Combined with the .N you can refer to the format, bitrate, suffix, and ending of every selected output file, for example {outputfiles.0.format} refers to the format of the first output file in your list of outputfiles:

• Output File 1 – format: WAV 16-bit PCM, bitrate: optimal, suffix: lossless, ending: wav
• Output File 2 – format: MP3, bitrate: 112 kbps, suffix: lossy, ending: mp3

For all available options, please see the Table of List Variables.

All Metadata Variables

The following variables are available:

For detailed use, please see Formatting Examples.

Conclusion

Metadata Variables are a powerful tool for organizing your productions whenever metadata values are set. Those field references are very convenient when distinguishing between different files at a glance, particularly when working with Presets, Batch Productions, or Watch Folders.

Please do not hesitate to contact us if you have any questions or feedback!

Cutting audio can be a rather tedious task. It requires a decent amount of time and is quite repetitive. Often silence segments, like speech breaks or breathing pauses, make cutting audio necessary in the first place.

Photo by Daniel Schludi on Unsplash

We introduce our new automatic silence cutting feature! It will make your life easier by saving you the time you would normally require to cut silence segments in your recordings.

Why do you need to cut silence segments?

Silence segments occur in your audio recordings naturally. They can be due to short speech breaks or breathing pauses. It's also possible, that at the beginning of a recording equipment needs to be re-adjusted, which also may result in a few seconds of silence.

Usually, listeners do not want to hear silence segments. The reason is easy: silence is redundant filler content. Hence, silence segments need to be cut to achieve a high-quality listening experience. Locating the segments and cutting them manually is tedious though and takes a decent amount of time for longer recordings.

This is why we developed and released our own automatic silence cutting feature.

How do we cut silence for you?

Our automatic silence cutting algorithm detects and cuts silence segments reliably. All you need to do is to enable the algorithm in your production - no further settings are required! This is the easiest possible way for you to cut silence in an audio file.

How to enable silence cutting for your production.

In our audio processing system, silence cutting is a multi-stage algorithm. We use our sophisticated voice activity detection algorithms to detect what is useful content and what is silence. Then we cut the silence parts and crossfade the remaining audio segments to make sure no audio artifacts are introduced. When cutting we ensure that intended speech breaks, e.g. between two sentences, remain untouched.

When we cut any audio, we make sure that chapter marks and speech recognition transcripts are adapted accordingly. Additionally, when exporting to other external services we make sure the cut tracks are exported and correctly labeled.

Audio Examples

Let's listen to two audio examples.

Example 1 (Singletrack production)

Here we have a singletrack production with three silence segments. The segments are located at the beginning of recording, between the first and the second "Hi" as well as at the end. Each silence segment is cut down to a length which still sounds natural, but does not annoy the listener.

The breathing onsets, which happen straight before voice kicks in again, are not cut. This makes sure that the character of the recording remains natural.

For this example, we also activated our new AutoEQ feature to remove pops in the audio.

Here is also a screenshot of how the result looks in our audio player. The gray areas show where our audio processing system cut the silence.

The result of example 01, as displayed by our Audio Inspector.

Thx to the Feel Free to Deviate podcast for providing this recording.

Example 2 (Multitrack production)

Let's also look at silence cutting in a multitrack production. This small excerpt of the TVEye podcast contains a music track and three speaker tracks. Before the intro music kicks in, there are a few seconds of silence.

The few seconds of silence at the beginning of the file are cut. After that, no further cuts are applied though to make sure the background music remains intact.

This is how the result of example 02 looks in our Audio Inspector.

Silence Cutting in our Audio Inspector

As you may have seen already in the examples, the cut segments are displayed as checked grey areas in the Audio Inspector. This is how they will be displayed by default.

Cut segments are displayed as checked gray areas by default.

During playback, the Audio Inspector will automatically skip these cut segments on the master track and play the silence segments if you activate the input track. This way, you can check each segment that was cut.

It's also possible to hide the cut segments. The following picture shows you how to do that.

You can also hide cut segments.

First, you must click onto the "?" icon in the bottom right corner to show the Audio Inspector options. Then you must toggle the "Silence Cut Region" switch. After that, the cut regions are not displayed anymore, and also won't be played back on the input track anymore.

If you click onto "Show Stats", you can activate the audio processing statistics. These statistics show you how much of your audio was cut, as well as the resulting track length after the cuts were applied.

The processing statistics tell you more about how much audio was cut.

Conclusion

With our automatic silence cutting feature, we went one step further towards the perfect audio assistant. Audio editing has been a tedious-but-necessary task for a long time, but with our automatic silence cutting feature, we just made it easier for you!

Feel free to send us your feedback - how do you like our new feature? Also, make sure to follow us, as we will release more automatic cutting algorithms for you in the future!

We're thrilled to introduce our Automatic Shownotes and Chapters feature. This AI-powered tool effortlessly generates concise summaries, intuitive chapter timestamps and relevant keywords for your podcasts, audio and video files.
See our Examples and the How To section below for details.

Why do I need Shownotes and Chapters?

In addition to links and other information, shownotes contain short summaries of the main topics of your episode, and inserted chapter marks allow you to timestamp sections with different topics of a podcast or video. This makes your content more accessible and user-friendly, enabeling listeners to quickly navigate to specific sections of the episode or find a previous episode to brush up on a particular topic.

Shownotes are also very likely to boost your show's Search Engine Optimization and eventually its popularity, leading to an increase in listeners.

However, especially structuring the content and finding useful positions for chapter marks is a very time-consuming process, that can be fully automated with our new feature.

Besides the obvious use of creating shownotes and chapters for podcasts, you can also use our new feature to easily generate an abstract of your lecture recording, take the summary of your show as the starting point for a social media post, or choose your favourite chapter title as the podcast name.

What happens behind the Scenes?

When the Automatic Shownotes and Chapters feature is selected, the first step is speech transcription by either our internal Auphonic Whisper ASR or any integrated External ASR Service of your choice.

Some open source tools and ChatGPT will then summarize the ASR resulting text in different levels of detail, analyze the content to identify sections with the different topics discussed, and finally complete each section with timestamps for easy navigation.
Beginning with the generation of a Long Summary, the number of characters is further reduced for a Brief Summary and from the brief summary a Subtitle and some Keywords for the main topics are extracted.

Depending on the duration of the input audio or video file, the level of detail of the thematic sections is also slightly adjusted, resulting in a reasonable number of chapters for very short 5-minute audio files as well as for long 180-minute audio files.

How to automatically generate Shownotes and Chapters in Auphonic

If you are a paying or beta user, you can automatically generate shownotes and chapters by checking the Automatic Shownotes and Chapters Checkbox in the Auphonic singletrack or multitrack Production Form with any of our ASR Services enabled.
Once your production is done, the generated data will show up in your transcript result files and in the well-known Auphonic Transcript Editor above the speech recognition transcript section.
By clicking on a chapter title in the Chapters section of the transcript editor, you can jump directly to that chapter in your transcript to review and edit that section.

Unless you have manually entered content before, the generated data will also be automatically stored in your audio files' metadata as follows:

• Generated Long Summary stored in metadata field Summary.
• Generated Subtitle stored in metadata field Subtitle.
• Generated Keywords stored in metadata field Tags.
• Generated Timestamps for thematic sections stored as Start Time of Chapters Marks.
• Generated Headlines for thematic sections stored as Chapter Title of Chapters Marks.

Please note that not all of our supported Output File Formats are designed to use metadata.
For details see our previous blog posts: ID3 Tags Metadata (used in MP3 output files), Vorbis Comment Metadata (used in FLAC, Opus and Ogg Vorbis output files) and MPEG-4 iTunes-style Metadata (used in AAC, M4A/M4B/MP4 and ALAC output files).

Example

As a real-life example, we automatically generated shownotes and chapters for the Lex Fridman Podcast #367: "Sam Altman: OpenAI CEO on GPT-4, ChatGPT, and the Future of AI".

Check out our transcript and generated shownotes:
LexFridmanPodcast367-transcript.html

Conclusion

The automatic generation of shownotes and chapters is a huge time-saver for podcasters and video creators, as it speeds up the tedious process of manually structuring and summarizing your content.

For now it is available for all paying or beta users. If you would like to become a beta user, or have any questions or feedback, please do not hesitate to contact us!

We all know the problem: the content is perfectly prepared, and everything is in place, but the moment you hit the record button, your brain freezes, and what pops out of your mouth is a rain of “ums”, “uhs”, and “mhs” that no listener would enjoy.
Cleaning up a record like that by manually cutting out every single filler word is a painstaking task.

So we heard your requests to automate the filler word removing task, started implementing it, and are now very happy to release our new Automatic Filler Cutter feature. See our Audio Examples and Usage Instructions below.

What is removed?

While the definition of filler words is not the same, depending on who you ask, some words can be used as filler as well as content. For example, “like”, “well”, “you know”, etc. cannot be removed without the risk of removing also content and destroying sentences, even if those words are used as filler words in some cases.

Therefore, we decided to focus on the removal of the obvious fillers, namely any kind of “ums”, “uhs”, “mhs”, German “ähm”, “äh”, “öh”, French “euh”, “euhm” and similar.

Audio Examples

1. English Male Speaker

The first audio example is an excerpt from the interview “From Racing Failure to Red Bull Champion: The Untold Christian Horner Story”. Our algorithm found and removed a remarkable ten filler words in this 45-second snippet:

Screenshot of the Auphonic Audio Inspector: each pale red shaded area corresponds to a cut-out filler word.

2. Austrian-German Female Speaker

The following example is an interview with the Austrian Ex-Foreign Minister, Karin Kneissl, who uses seven filler words within 26 seconds:

Usage Instructions

To use the Auphonic Automatic Filler Cutter feature, you just have to create a production or preset as you are used to and select “Cut Fillers” for “Automatic Cutting” in the section “Audio Algorithms”:

When your production is done, all cut-out filler words will appear as pale red shaded areas in the Auphonic Audio Inspector on the production status page, as you can see in the upper screenshot of the Audio Inspector.

If you want to remove silent segments from your audio as well, please also enable our Automatic Silence Cutting feature.

NOTE: Our Automatic Cutting features (for filler and silence) are not available for video files!

Behind the Scenes

For the training of our Automatic Filler Cutter AI-Algorithm, we created datasets that contain manually labeled audio files, collected from 'real world' audio data. So far, we have labeled, trained, and tested the system with English, German, Spanish, and French data.

However, in the Auphonic Web Service, you can activate and test the Automatic Filler Word Cutter for all languages. We would be very happy to hear how the filler removal works out for completely different-sounding languages from, e.g., the Asian, African, or Slavic language families.

Please send us feedback on any problems or error patterns you discover! This will help us generate specific data for the training to improve the algorithm and eliminate your problems.

Conclusion

Automatic filler word cutting is a powerful tool for podcasters looking to enhance the quality of their content. It boosts clarity and professionalism, all while making your editing process more efficient. Some users, however, see a touch of authenticity in filler words within podcasts. So, we leave it up to you to enable or disable the Automatic Filler Cutter feature for your next Auphonic production, depending on your desired style.

We are currently working on filler word cutting optimizations for more languages, so watch our channels to get all the news on our upgrades!

If you have any feedback for us – how the filler cutter is working in your language, what you do or don't like, what you miss, what else you would want to remove from your audio besides silence and filler words, etc. – you are welcome to contact us via email or directly comment on our production interface!

We're excited to roll out an upgraded version of our Transcript Editor, focusing on enhancing your transcription workflow and making it more intuitive, especially for mobile users. This overhaul introduces several key improvements and features designed to streamline the transcription process.

Click here for a Live Demo

What's new?

Line by Line Editing

Your transcript is being rendered line by line. This allows for precise editing of every single timestamp. Depending on the speech recognition engine editing can be done on word or phrase level.
For optimal results, we suggest utilizing our Auphonic Whisper ASR engine.

A paragraph with 9 lines, every line represents a "subtitle line" (.vtt, .srt).

You can split or combine paragraphs and lines using the Enter and Backspace keys. Our new Playback Slider enables seamless scrolling through the text, while we highlight the currently selected word as you go. With the switchable Play on Click function you can start your playback from anywhere in the transcript.

Automatic Shownotes and Chapters

If you enable Automatic Shownotes and Chapters in the Production form, we include AI generated shownotes and chapters directly into the Transcript Editor. You can edit Chapter Times and Text directly within the Transcript Editor. Once you click Save (top right), any modifications made within the shownotes and chapters will also be saved back to the production.

Screenshot of Automatic Shownotes and Chapters withing the Transcript Editor.

You are also able to edit chapter times directly within the transcript editor. Please note that this only works within the Transcript section of the editor to ensure precise placement of chapters.

Screenshot of Edit Chapter Time.

Local History: Undo and Redo

Our Local History feature offers convenient undo and redo functionality. This means you can effortlessly revert changes or redo them as needed, providing you with greater control and flexibility during the editing process.

Edit Speakers

Our revamped Transcript Editor automatically assigns speakers in Multitrack Productions. You can use the Track Identifier in our production form to assign speakers and easily edit, remove, or add new ones within the Transcript Editor. So it's clear who says what at any time!

Screenshot of Edit Speaker.

Confidence Highlighting

Within the transcription areas of low confidence are highlighted with our Highlight Low Confidence feature. So you can check up on the AI and edit words it is not entirely confident about! It also shows you how confident the AI is about the specific area if you hover over it.

Offline Mode

This feature enables you to download and share the Transcript Editor for offline editing. This means you can share the *.html file with someone else for editing purposes. Simply use the Download Editor action to obtain an offline version of the Transcript Editor.

Export Transcript

You can export your transcript in all currently relevant formats (.srt, .vtt, .txt, .html, .pdf) and include them in your publishing process or video editing software.

Screenshot of Export Transcript.

Responsive Design

We want to make podcasting as easy as possible. The responsive design of our Transcript Editor allows for fast editing on mobile devices - so you can edit what you're saying anywhere, anytime!

Screenshot of Transcript Editor on a mobile device.

Why use it?

Apple Podcasts paved the way for all podcasts to feature transcripts, so users can read through what you are saying and look for specific parts of your talk they're interested in revisiting. That could be book recommendations, advertisements or one of your ideas you want to share with the world.

We're trying to make the transcription process as automated and easy for you as possible. Especially when using Multitrack Productions we strive to take all the work off of you and let the AI do its magic.

Additionally, we aim to simplify manual corrections wherever automated processes encounter challenges, ensuring that even these adjustments are as effortless as possible.

Try it now on auphonic.com!

Feedback

If you have feature requests or feedback for our new Transcript Editor, please let us know! You can also leave a comment in the feedback section on the status page of your specific production.
We're looking forward to hearing from you!

We're excited to announce the release of our new speaker diarization feature! With our latest update, we can now detect individual speakers within a single audio recording, allowing users to see precisely who said what and when. This information is then reflected in the transcript.
Previously, this feature was only available in Multitrack Productions.

What is Speaker Diarization?

Speaker diarization is the process of identifying different speakers and segmenting an audio file accordingly, making it easier to accurately determine who said what. This is particularly useful in scenarios like meeting recordings, interviews, and podcasts involving multiple speakers.

What's New

Until now, Auphonic users had to use our Multitrack Production Workflow to gain access to speaker identification. With our recent update, this feature is now also accessible for single track productions, thereby further simplifying our workflow.

How It Works

When selecting Auphonic Whisper ASR as your speech recognition engine on our production page, the option to use “Speaker Detection” appears. You can select the number of speakers in the recording yourself, or have the AI identify and label them automatically.

Select "speaker detection" in the speech recognition menu

The identified speakers will then be shown next to what they said in the captions of our audio player and within the generated transcript. We know exactly who is saying what at any given time.

If you need to change speakers' names, you can edit them in our Transcript Editor. By changing the name of the speaker, the changes will be applied automatically within the whole transcript.

Click here for an example transcript to play around with!

The transcript editor also lets you edit the generated transcript's content and correct any mistakes. This gives our users the final say in quality control.

For more information on how to use our transcript editor, click here!

Conclusion

With our newly released speaker detection feature for single track productions, we simplified the automatic transcription process even further. You can drop a single audio file into our algorithms, the AI automatically detects and transcribes its contents and attributes speakers correctly. And if the model should unexpectedly be wrong at any time, you can correct it in our Transcript Editor.

Feedback

We're looking forward to having you utilize our new speaker diarization feature!
Please, feel free to send us feedback through our Contact Form or submit it directly in the status page of your production.
Happy detecting!

The new Auphonic team accounts streamline billing for companies, teams, or groups and are available to business users. A team account's owner can invite team members and admins, all of whom share the team account's credits for their productions.

The team account feature only impacts billing. Team members cannot access each other’s productions, presets, etc.
If you're interested in switching to a team account, please contact us!

What are Auphonic Teams?

A team consists of an Owner with Members and optional Admins. The Owner and Admins can add and remove team members as well as change their roles in the team. Every added account can use Auphonic as usual, but only the account Owner's credits are used for billing productions.

This simplifies the invoicing process for teams using multiple Auphonic accounts.
One Owner provides the credits, and all of the team can use them.

Overview of the team accounts section in the account settings.

Inviting Users

After gaining access to the team account feature, you can invite new team members via the team account section on the account settings page. Invited team members can be:

• Existing Auphonic users
• New users who do not yet have an account

Managing Team Account Members

The team account Owner and Admins can remove members and change roles within the team.

Editing roles

Roles and Permissions

Within the team, there are three roles: Owner, Admin and Member. Each role has specific permissions:

All roles and permissions.

Billing

The Owner of the team account is responsible for purchasing credits. Productions made by team members will use the team account's credits. As a team account member, you will see the team account owner's credit balance instead of your own.

If you wish to access your personal credits, you can leave the team at any time.

Conclusion

With the introduction of team accounts, we provide a solution to simplify the production process for teams. One account is responsible for providing the credits and all team members can use them collectively!

Contact us if you are a business user and interested in using our new feature.

Feedback

We are always happy to receive feedback on our features!
If you have thoughts, ideas or recommendations, drop us a line using our contact form or email us directly.

We're looking forward to hearing from you!

As a portrait photographer, you know that the heart of your business beats in the rhythm of capturing souls through lenses. But here’s something not many will tell you: there’s an art to portrait photography pricing too.

Just think about it. How do you put a price on immortalizing someone’s personality in a snapshot? You’re not just pressing buttons; you’re creating magic!

You might be wondering, “How can I create my own masterpiece when it comes to setting prices?” Or perhaps thinking, “I don’t want to undersell myself or scare away potential clients.”

Understanding Portrait Photography Pricing

If you’re a professional photographer or someone considering getting into the photography business, it’s essential to grasp portrait photography pricing. Figuring out portrait photography pricing may appear complicated at first, yet with some knowledge of the business’ fundamental principles and procedures it will all start to become clear.

The number one thing to avoid when pricing your photography is spending more than you make. You need to price your images based on time spent behind the lens and editing them post-shoot as well as the market value of your work.

Just imagine, you’ve launched a brand-new online store filled with products that you know are just perfect for your target audience. You’re excited and ready to make those sales, but there’s one piece of the puzzle missing – high-quality product images. And then it hits you: “How much is this going to cost me?”

No doubt, we all appreciate visually stunning product photos when shopping online. Have you ever considered what goes into producing those eye-catching product images? Or how their quality can dramatically impact your sales?

The truth is, professional-looking visuals can significantly influence purchasing decisions – upping conversion rates while fostering trust with customers. Yet finding an experienced product photographer within budget who also understands your vision isn’t always straightforward.

Let us help you.

Understanding Product Photography Pricing

Navigating the realm of product photography pricing can be like trekking through a jungle without a map. You’ll find rates that range from surprisingly affordable to astonishingly high-end, making it tough for businesses to get their bearings.

The cost of product photography is dependent on a variety of elements,

Picture this. You’re hosting the event of a lifetime, and you want every magical moment captured perfectly. It’s no surprise that finding the right photographer is high on your list. But how do you navigate through event photography pricing?

You might assume that requesting a quote is as straightforward as dialing the number…but be prepared to be surprised! The cost can be influenced by factors like experience level or type of event – there’s more to consider than meets the eye. You can also use this guide as a new photographer to figure out how much you should charge for different types of events.

In this guide, we’ll delve into everything from understanding why photographers charge what they do, to examining costs associated with different types of events such as weddings or corporate gatherings. We’ll also take an exciting journey exploring common pricing structures used by photographers and breaking down additional services and costs that may sneak up on you when hiring an event photographer.

Understanding Event Photography Pricing

If you’ve ever wondered how event photography pricing works, this section will shed some light on it.

There’s a dance of light and shadow you can’t quite grasp until you’ve seen a lighthouse cut through the fog. Mastering lighthouse photography means capturing that silent symphony between nature and human ingenuity, each photo telling its own epic tale.

I remember setting up my tripod on rocky shores, waiting for that perfect moment when the sun dips low enough to paint everything in gold. You’ll get why timing is crucial, how early morning or late afternoon gives your shots character with just the right color wash over stunning structures.

This journey will equip you with gear know-how—like picking out wide-angle lenses for grand scenes or telephoto ones for details—and dive into camera settings so those beams look as majestic in photos as they do slicing through ocean mist.

Capturing the Romance of Lighthouses Through Photography

Lighthouse photography captures more than just a structure; it seizes the tales of human ingenuity and nature’s raw beauty. These coastal sentinels have long stood against time, their beams slicing through fog and darkness, guiding sailors home.

The Allure of Coastal Sentinels

There’s something inherently romantic about lighthouses.

Words and tools are powerful, but are they our only way of making a mark? *Pause for emphasis* Stephan Moccio doesn’t think so. An artist, composer, and producer, he’s the name behind some of the most well-known songs and soundtracks on the planet. But surprisingly enough, all that success with sound has come through silence. In this podcast, I have the privilege of sitting down with him to discuss how strategic refrain and thought can benefit creative power. Creativity as a Muscle Skill can come naturally, but people rarely get to the top through their natural-born talents alone. Even 6’9″ LeBron James wouldn’t be where he is as a basketball player without putting in the unseen hours of success. Whether physical or mental, training effectively determines performance. “I’ve learned that to get great things and to achieve great things requires a lot of work behind the curtain…” Creative practice isn’t different from other forms of training in that making a habit out of it is hard. We all have lives outside of our passions, and those passions aren’t always fully funded. Many of us work day jobs while pursuing creative endeavors. Stephan has had to balance paying bills, raising a...

The post Stephan Moccio: The Power of Pauses in Life (and Music) first appeared on Chase Jarvis.

The post Stephan Moccio: The Power of Pauses in Life (and Music) appeared first on Chase Jarvis.

In this episode, Ryan Holiday explores the timeless wisdom of Stoicism and its relevance to contemporary challenges. A frequent guest and renowned author, Ryan discusses his latest book, “Right Thing. Right Now.: The Necessity of Doing What’s Right – Even When It Isn’t Easy,” the third installment in his Stoic Virtue series. Emphasizing justice as the cornerstone of courage, wisdom, and self-discipline, Ryan draws on historical examples from Marcus Aurelius to Gandhi to illustrate the transformative power of ethical living. Some highlights we explore: How to make a meaningful impact by focusing your efforts on specific problems. The development of the Stoic Virtue series and its modern relevance. Practical advice for navigating ethical decisions in complex situations. How to make stoic principles more relatable. How one balances speed and quality in the creative process. And much more! Enjoy! FOLLOW RYAN HOLIDAY: instagram | twitter | website Listen to the Podcast Subscribe  

The post Ryan Holiday: Stoic Values to Change Your Life first appeared on Chase Jarvis.

The post Ryan Holiday: Stoic Values to Change Your Life appeared first on Chase Jarvis.

In this episode, Professor Alison Fragale, an expert in organizational psychology, discusses the fascinating dynamics of power and status and how they shape our lives and well-being. We dive into the differences between power and status, why both are essential human needs, and how their presence or absence affects our mental and physical health. Professor Fragale shares actionable strategies to help anyone elevate their status, build influence, and navigate power dynamics with authenticity. We also touch on the challenges of gender and racial status, the importance of autonomy, and practical tactics like leveraging your network and social media to boost your influence. Some highlights we explore: The critical difference between power and status, and how both impact your life. Practical strategies for building influence and maintaining authenticity. The role of gender, race, and autonomy in navigating power dynamics. And more! Enjoy! FOLLOW ALISON FRAGALE: instagram | linkedin | website Listen to the Podcast Subscribe

The post Game-Changing Tactics to Elevate Your Status first appeared on Chase Jarvis.

The post Game-Changing Tactics to Elevate Your Status appeared first on Chase Jarvis.

In this episode, Stanford behavioral scientist Dr. Jamil Zaki unpacks the power of trust and the dangers of cynicism. We dive into how our beliefs shape our reality, with trust leading to incredible social and economic gains, while mistrust spirals into cynicism. Dr. Zaki shares insights on empathy, the post-pandemic rise in disconnection, and practical ways to break free from negativity, emphasizing the importance of real-life connections over media-driven cynicism. This conversation is packed with actionable advice on how to foster trust and spread optimism in our daily lives. Some highlights we explore: The ripple effects of trust and mistrust. Practical strategies to challenge and overcome cynicism. The role of media in shaping our perceptions and how to stay grounded. And more! Enjoy! FOLLOW DR. JAMIL ZAKI: instagram | twitter | website Listen to the Podcast Subscribe

The post Simple Trick to Build Trust in Your Creative Collaborations first appeared on Chase Jarvis.

The post Simple Trick to Build Trust in Your Creative Collaborations appeared first on Chase Jarvis.

Feeling uninspired and exhausted? Discover how to overcome creative burnout with these 4 actionable strategies to reignite your passion.

The post Creative Burnout Destroying Your Passion? (Try These 4 Quick Strategies) first appeared on Chase Jarvis.

The post Creative Burnout Destroying Your Passion? (Try These 4 Quick Strategies) appeared first on Chase Jarvis.

In today’s world of online gambling which is constantly changing, cross-platform development is essential for success. Players want to be able to play their favourite casino games on mobile phones as well as tablets or desktop computers but this presents [...]

Read Article

The post Cross-Platform Development: Coding for Online Gaming on Multiple Devices first appeared on CSS Reset.

Digital trading services have transformed the investment landscape for stocks, commodities, and other financial instruments. But do you know what’s true and what’s not about these services? Let’s dive into the common misconceptions surrounding digital trading and distinguish between myth [...]

Read Article

The post What Are the Common Misconceptions about Digital Trading Services? first appeared on CSS Reset.

The logistics industry has experienced a meaningful changeover with the appearance of the Internet of Things (IoT). By enabling real-time data collection and analysis, IoT has supplied new visibility into logistics operations. This raised visibility is key for keeping up [...]

Read Article

The post The Internet of Things in Logistics: Real-Time Data for Enhanced Visibility first appeared on CSS Reset.

Welcome back to another icon dedicated tutorial, in which we’re going to learn how to quickly create a computer settings icon inside of Figma, using nothing more than a couple of basic geometric shapes. So, assuming you already have the software up and running let’s jump straight into it! Tutorial Details: Computer Settings Icon Program: […]

The post How to Create a Computer Settings Icon appeared first on Vectips.

In today’s tutorial, we’re going to take a quick look behind the process of creating a security icon, and see how we can take some simple shapes and turn them into a finished usable product. So, assuming you already have Figma running in the background, let’s jump straight into it! Tutorial Details: Security Icon Program: […]

The post How to Create a Security Icon appeared first on Vectips.

Welcome back to another Figma based tutorial, in which we’re going to take a quick look behind the process of creating a phone widget app icon, using nothing more than a couple of basic geometric shapes. So, assuming you already have the software up and running let’s jump straight into it! Tutorial Details: Phone Widget […]

The post How to Create a Phone Widget App Icon in Figma appeared first on Vectips.

Hey, welcome back to another icon tutorial, in which we’re going to explore how to create a messaging app icon in Figma, using nothing more than a couple of basic geometric shapes, that we’re going to adjust here and there. Tutorial Details: Messaging App Icon Program: Figma Difficulty: Beginner Topics Covered: Compositional Construction, Shape Alignment, […]

The post How to Create a Messaging App Icon in Figma appeared first on Vectips.

Create a quick and trendy office vector scene with simple line icons. We’ll go through each piece, step by step in no time flat! Tutorial Details: Illustrate an Office Vector in 15 Minutes! Program: Adobe Illustrator CS6 – CC Difficulty: Intermediate Topics Covered: Design Theory, Shape Building, Compositional Skills Estimated Completion Time: 15 Minutes Final Image: […]

The post Build a Trendy Line Icon Office Vector Scene in 15 Minutes! appeared first on Vectips.

I read this line on a website. “Apple diehard fans would be tempted to buy a live pig if it had the familiar logo branded on its backside”. Ha! I wondered what that might look like, so I tried to draw a picture in my mind and this was the outcome. Jokes aside people, I...

The Australian Government has recently announced new English language requirements for Student and Temporary Graduate visa applications. These changes are intended to ensure that international students and graduates have a solid command of the English language to successfully participate in academic and professional settings in Australia. New English Language Requirements Under the updated visa application […]

The post English language requirement tightened for Student and Temporary Graduate Visa Applicants appeared first on Australian Visa Experts.

On Wednesday 12 June 2024, the Minister for Home Affairs the Hon. Clare O’Neil MP announced changes that will stop certain visa holders being able to make further visa applications onshore. These changes will come into effect on 1 July 2024. The focus of these changes rests on student and other temporary visa holders. As […]

The post Minister for Home Affairs announces changes to onshore visa applications to stop ‘visa hopping’ appeared first on Australian Visa Experts.

Winterlichter Palmengarten Jan 2016

Photos from my annual trip to see the christmas lights in the botanical gardens in frankfurt

Co.Design asked Tobias Frere-Jones of Hoefler & Co. to give his thoughts on Apple’s choice of Helvetica as an interface typeface for the upcoming OS X Yosemite update:

Despite its grand reputation, Helvetica can’t do everything. It works well in big sizes, but it can be really weak in small sizes. Shapes like ‘C’ and ‘S’ curl back into themselves, leaving tight “apertures”–the channels of white between a letter’s interior and exterior. So each shape halts the eye again and again, rather than ushering it along the line. The lowercase ‘e,’ the most common letter in English and many other languages, takes an especially unobliging form. These and other letters can be a pixel away from being some other letter, and we’re left to deal with flickers of doubt as we read.

This reminds me of what Erik Spiekerman wrote about Helvetica:

[Helvetica] really wasn’t designed for small sizes on screens. Words like milliliter can be very difficult to decipher. If you ever had to read or write a password with 1, i, l or I, you know the problem.

Still, I wouldn’t keep Lucida Grande for HiDPI displays. With a 2× resolution jump (4× pixels) pixel fitting becomes less of an issue, and pixel optimized typefaces like Lucida Grande begin to look crude in comparison with typefaces made primarily for print. Legibility obviously still matters just as much, but the choice need no longer be bound to fonts optimized for low resolution displays.

Min Ming Lo analyzes the various designs of the share icon currently in use. He concludes:

The best icon is not the one that is the simplest, nor the one that makes the most sense. Instead, the best icon is one with which most users are already familiar. An effective icon is one that requires minimum effort for the user to translate that symbol to an action.

I think part of the problem with coming up with a good share icon is that the concept of sharing physical items doesn’t directly map onto the concept of sharing digital resources, which oftentimes simply involves posting a link on a public feed. The latter is closer to broadcasting a message rather than dividing up a resource or experiencing a thing simultaneously. Icons with more specificity – e.g. a tweet icon, a Facebook like icon – are unambiguous; they relate directly to a service and the kind of interaction that service allows. Trying to cover them all with an umbrella of “sharing” is difficult, if not impossible, to do clearly.

The problem doesn’t lie in the icon, but in the vagueness of what it represents. For this reason I think Apple’s icon resembling an upload action is probably the best choice because what it represents is not so much sharing but putting the content somewhere else. Whether the full file is uploaded or just the link is given doesn’t really matter, what matters is that the thing in question is transmitted somewhere. It’s also worth considering whether the fight for an icon-only button is worth it, and that it may not be easier and better to just use the words “share” to describe the action. There’s a reason why the stop sign just says “STOP” – you can represent it with something else, but the negative effect on clarity is just not worth it.

Joel Unger approaches the blurry, semi-transparent window aesthetic, recently introduced in iOS7 and now making its way to OS X Yosemite, from the standpoint of evolutionary biology. He argues that the reasons for this latest trend, as well as other trends, are: 1) the visual effect is relatively rare, and 2) the effect is expensive to achieve (in this case expensive in terms of graphics processing power). Both of these go hand in hand given that what is expensive to achieve is probably also going to be rare, at least for the period it still remains expensive. While these two things are initially the differentiator for the trendsetter, they will inevitably be mimicked by others, resulting in a design trend.

Curt Arledge ran a user test to find out whether hollow icons perform any different to solid icons. Hollow icons are an icon aesthetic popularized by iOS7 – icons that are composed of thin lines rather than filled in shapes. It was previously theorized that this icon style required more cognitive processing, and thus would perform worse than typical solid icons.

Arledge found no significant variation between the icon styles. One combination performed worse than others: white hollow icons on a black background. Others performed similarly, irrespective of whether the icon was on a white or black background. What seemed to matter most is not the style itself but how meaningful the design of the icon itself is. For example, a filled in speech bubble is less recognizable than a hollow one because a speech bubble is something that is often depicted as an outline. On the other hand, an outline doesn’t add anything to the icon of a cloud, so a solid shape performed better in that case. Arledge also found that the lock icon performed the worst. Looking at the lock icon used in the test one could guess why: the thing has no keyhole, and so looks just as much as a shopping bag as it does a lock. Adding a keyhole would likely provide enough of a clue to dispel the confusion. The takeaway here is that the style doesn’t really matter – at least not enough to make a significant difference. What matters is how well the icon represents its object. If the icon is good, then it will work whether or not it is implemented as a solid shape or as an outline.

Delphine Joly Pujol est l’âme poétique et inspirée qui se cache derrière OcciD Créations. Issue du milieu de la biologie, dont elle emprunte le vocabulaire pour intituler ses collections, l’artiste est passionnée de céramique depuis 15 ans. Fascinée par la naissance d’une pièce à partir des quatre éléments que sont l’eau, la terre, l’air et […]

Le Prix Picto pour la photographie de mode 2022 a dévoilé ses lauréats : Christopher Barraja remporte le Grand Prix, Camille Brasselet le deuxième et la dotation le19M et Antoine Henault le troisième prix ainsi que la dotation Filippo Roversi. La cérémonie de remise des prix a eu lieu le mardi 19 avril au Palais […]

Depuis son plus jeune âge, Sami Bencheikh arpente le Sud-Ouest de la France. Interne de radiologie à l’hôpital de Bayonne, il a débuté la photographie au début de ses études de médecine. Motivé par de grands photographes comme Ben Thouard pour ne citer que lui, il a trouvé en l’océan un refuge au stress du […]

Whether you're a project manager or a startup business owner, most of you lack the time or the in-house experts to help with product design. Product design ...

The emergence of AI software in the field of architecture and design has sparked a significant shift in how professionals approach their work. With advancem ...

Tom and Jerry, the mischievous cat and clever mouse duo, have been captivating audiences for generations with their hilarious antics. As a child, I was capt ...

Discover our special freebie: vector frames in Y2K style, perfect for your 2000s fashion aesthetic projects. Download now for free! Vector frames are a co ...

New realistic Marvel art brings characters to real life from the X-Men '97 TV show. 2024 marked a new beginning for the X-Men: The Animated Series, as the f ...

Discover free, high-quality vector wings for your creative projects. Download royalty-free designs, from tribal wings to angel outlines. Elevate your tattoo ...

As per scientists around 90% of all information we perceive comes through our eyes. The visual side always has been quite important for humanity, we can see it from the culture of writings and visual art having very long history. The other suitable feature is laconism. We can experience the lack of time for finding […]

Stock photography business has become trend. It could be seen from the number of stock photography providers or so called microstock agencies in the internet which is increasing. The number affects the effort of every microstock agency to survive and get much buyers as possible. As a result, we can see so many microstock agencies […]

When you're working in Adobe Illustrator, you may need multiple layers. And when we're talking about having multiple layers, it's easy to confuse layers with artboards. However, duplicating layers and duplicating artboards are not the same. You can have multiple artboards (or canvases) in Illustrator, and you can create multiple layers on a single artboard....

The post How to Duplicate a Layer in Adobe Illustrator appeared first on Bittbox.