• Feature in SonicSell: We added the ability to create an audio advert without sound designs 💯
• Updates placeholder text for sonicsell and workshop 💯
• We made bug fixes in our logging for data sharing.
• https://audiostack.ai is now compliant with cookie regulations! 🔒
• We improved the reliability of our VAST server by over 20x - contact your account manager for details about this.

Bumper improvements 🚀

We made a bumper set of improvements this week 💯

Better sound quality with media files

•  We enhanced the mastering sidechain compression for music using media as key signal, allowing to combine File Manager with TTS audio in the mix in a leveled way. This enables better sound quality in more situations 😀

API Bug Fixes

• 🐛We made some improvements to the Audio Evaluation Service bugfixes
• Better Errror handling improvements when Files were Not found ⚠️

Platform fixes and bug fixes

• 🚀 Rebranding of Audio Playground to Workshop
• 🐛We fixed a bug to always show org switcher
• 💚We fixed the "you are not authorised" flashing when page loads
• 🐛 fixed re-rendering in asset card and a bug with the play button
• 🐛fixed indexed Db error when db is manually deleted
• 🚀 We added new icons to the platform add-new-icons-to-platform
• 🐛 We fixed some bugs in the library
• 🐛 fixed ghost card bug

Platform and SDK features and improvements

• 💯 SDK for Suite endpoints, long polling and error handling. You can check it out now in the Python SDK
• 💯 added lazy mode to asset cards to enhance the customer experience
• 💯 Added pagination to library so now it will load faster 🐎
• 🐛 fixed conditional for play button icon in asset card
• 🐛 We updated default sound design to soiree_a_illangeacross all workflows

JS SDK v1.1.11

We improved the JS SDK and launched a new version https://www.npmjs.com/package/@aflr/audiostack

• Integration with STS (speech to speech) Endpoints:

• https://v2.api.audio/speech/sts/voices (GET to get a list of speech to speech voices available)

• https://v2.api.audio/speech/sts (POST to start an sts pipeline)

• https://v2.api.audio/speech/sts (GET to get the status of the pipeline launched)

Performance improvements 🚤

Speed improvements for SonicSell, which was causing some errors

1. Reducing deployment package size of ms-script. ~600ms faster.
2. Calls to recommend mood/gender/tone in parallel, saves 4-5 seconds.
3. We reduced cold starts in our infrastructure also yielding up to 1.8 seconds saving.

This should make your experience much faster 🚤

Today we added a new guide to our documentation, to help AudioStack Platform users understand the different advanced Audio Tools that are available in the Files view, inside Resources > Content. Audio Tools include an evaluation service to check the quality of uploaded files, a denoiser, and stem separation to allow you to extract voice and music from any uploaded file.

Find out more: https://docs.audiostack.ai/docs/audio-tools.

AudioStack python SDK 2.0.0 released:

• Removed support for end-of-life python versions 😀
• Fixed bug - Added missing required arg to pass project to content.list_modeules 🐛
• Fixed bug - Added missing x-assume-org header to File.download_url
• Added linting, typehints and code formatting to CI/CD to make easy to read code for our users 💯
• Added poetry package management to align with our best engineering practises - WE LOVE POETRY! 🤓
• You can install this with pip install -U audiostack 🚀

Docs Docs Docs

We're constantly working on enhancing our docs based on customer feedback 🚀

We've just added these two examples this week.

• https://docs.audiostack.ai/docs/how-to-add-multiple-speakers-to-one-script Added an example to the docs with multiple speakers in one script 🔈 🧑‍🦲
• https://docs.audiostack.ai/docs/comparing-two-voices-by-the-length-of-their-speech - Added an example to compare the length of two voices in seconds.

Broadcasting your content

https://docs.audiostack.ai/docs/broadcasting-your-content
Delivery release 2.3.1:

• Adding an endpoint to purchase broadcasting rights for an audioform

• As soon as audioform is stable and released to users, they can get a license and be sure to have the broadcasting rights for a produced asset

New voice provider Respeecher 🇺🇦

• Respeecher voices published!

• We added 95 new voices to the platform

• You can see a short Loom video here - https://www.loom.com/share/362954519adf43b9bfc5fd481e18da9a

AudioForm v1.1.0

• Audioform expresses audio production in a json format and includes the definition of content, speech, sound design, and production elements. It is a novel approach to audio production and offers a number of advantages:
• Leverage the most recent development in AI audio creation
• Making audio production scalable
• A way to "build" audio that is developer-friendly
• A standardised way to facilitate echange across platforms

There's still a lot to improve but here's the first iteration step.

• Added TTS reduce endpoint to SonicSell flow in Audioform, making the TTS in v6 always fit in the ad's duration.
• We've also added it to Audio Playground as well.

JS SDK:

• Added pipeline polling to JS SDK and updated Suite types (related to handling pipeline statuses in Platform that will be released later)

Speech to Speech

ms-sts is now live in prod with 3 new customer facing endpoints:

• get_voices

• post_sts

• get_sts

The first lists the voice available for STS. The others are used to start and get the status of a STS pipeline using our internal mono-audio-suite.
In this release 11labs public and private voices are available and works for files up to 50 mb.Documentation available here:
https://docs.audiostack.ai/reference/getspeechtospeechvoices
https://docs.audiostack.ai/reference/postspeechtospeech
https://docs.audiostack.ai/reference/getspeechtospeechpipeline

https://docs.audiostack.ai/docs/examples-production

New platform release

• fix(platform): Fixed SideBarContent filtering by @carlosaore in https://github.com/aflorithmic/fe-audiostack-platform/pull/493
• refactor(analytics): Refactored trackEvent to useTrackEvent to include the new analytics endpoint by @carlosaore in https://github.com/aflorithmic/fe-audiostack-platform/pull/467
• feat: Wireframing for AudioPlayground audio generation   by @Louis in https://github.com/aflorithmic/fe-audiostack-platform/pull/492
• fix(library): disable analytics
• feat(adLibrary): Adding new Ad Library workflow page. You can see it under Essentials -> Library

• We added new developer plans
• Voice library spatial navigation
• We made improvements to Sonic Sell V6 - to set us up for the future.
• We add endpoint to generate audioform template.
• Now only successfully produced ads will now be saved

• 🐛Bug fix for Voice-Library Cards returning a 403 error;
• Improved our billing updates - improving our billing experience;
• We added enhanced voice permissions for private voices 🔒;
• https://docs.audiostack.ai/docs/examples We added some more examples to the docs, so you should be able to get up and running faster;
• We added the ability to handle media files on top of sound templates so you can now upload your own media files/ speech files and overlay them on top of sound templates;
• We improved several error messages throughout the platform - leading to a better user experience;
• Add error feedback when users upload a file >1MB or not JPG/PNG for the UserPicture. ⚠️

Better media experience

• We added startPadding and endPadding in section properties for better control of your production.

Here's an example of it being used

SECTIONPROPERTIES= {
    "section1": {"startPadding":2.0, "endAt":5.0, "alignment":"left"},
    "section2": {
        "startPadding":2.0, "endAt":10.0, "alignment":"left"},
    "section3": {"endAt": 40, "alignment":"left"}   
}
print(f"Creating your mix...")
mix = audiostack.Production.Mix.create(
        speechItem=speech,
        soundTemplate="example_sound_tempalte",
        timelineProperties={"fadeIn": 0, "fadeOut": 0},
        masteringPreset="balanced",
        sectionProperties=SECTIONPROPERTIES
    )

You can see more docs at Advanced Timing Parameters

We made a bunch of improvements to the platform.

Website update 💯

We made some big changes to our website, improving our design and adding some great new pages. Thanks to the team who worked on this

• https://audiostack.ai/enterprise
• https://audiostack.ai/developers
• https://audiostack.ai/en/blog

Bug fixes and improvements

• Updated file regexes and added decodeURIComponent 
• Fix get colors from org logo error 
• Aesthetic improvements to the sign up flow 
• Add error info on upload Org Profile Picture
• Platform Dashboard Redesign
• Beta Release of SonicSell V6 (enabled for ReleaseRadar only) 
• Audioform/sonicsell endpoint now supports creating more than 1 asset. Exposed through versions to create
• Updated the TTS endpoint to support maxLength per sections. will be used in the sonic sell audioform endpoints.

Docs improvements

• We added some new docs and improved the docs page.
• https://docs.audiostack.ai/docs/writing-a-news-page-audio-summariser
• https://docs.audiostack.ai/docs/using-the-api-to-generate-fully-produced-audio

Reducing bias in our models and systems

One of the challenges with AI models is bias. This is well documented - and has been discussed elsewhere like here
We shipped significant changes, by applying better guard rails and using our proprietary AI guard rails

These changes lead to:

• more gender diversity (before: ~ 1/3 male voices, now: ~50% male/50% female
• less gender mismatches (avoiding e.g. “Hi, I’, m Sarah…” spoken by male voice
• less gender-biased outcomes (e.g. ads on cleaning products have same chance for male/female voice)

Improvements and enhancements

🚢 Example files for new/existing organisations 🚀

• By default an example folder (audiostack_examples) with mediafiles and assets will be created when a new organisation is created. This means you can get started sooner.
• Suite and recommendation endpoints added to the JS SDK
• Shipped some modifications on speed calculation of Spanish ads in SonicSell, which improve ads that are too slow. 🇪🇸
• We added attribution in the Library to http://generated.photos who provide our generated images for our voices.

Beta feature

📘

Beta feature

Please contact support[at]audiostack[dot]ai if you wanted to be added to this

Whitelabel Support

We added a dynamically generated color banner based on org logo

We've been busy refreshing our sound templates, to make our licensing simpler and ensure the content we offer is suited to your most common AudioStack usecases. As a result, we've added a whole bunch of new Sound Templates in both the API and platform, and will be removing outdated "demo" templates at the end of May.

🚧

If you're currently using "demo" sound templates either via the platform or the AudioStack API, you will need to switch to alternative sound designs.

If you're struggling to find something that meets your needs, please contact support [at] audiostack.ai.

37 Demo Sound Templates to be Removed ⚠️

Sunny Skies
Surfing Dog
Laid Back Funk
Newsflash
Ethereal Dream
Power Sports
Garage Banger
Vintage Swing
Trailer Beast
Friendly Electro Pop
Bullmarket
Relaxed Vacation
Dark And Unsettling
Wild Beast
Feeling Good
Friendly Fantasy
Runway Rhythm
Cool Industries
Chopper Horns
Hotwheels
Epic Brass Trap
Pulse
Piano Artist
Fascinating Technology
Clap Together
Chopper Strings
Rockabilly Mischief
Relaxmas
Epic Pace
Stepping Up
Welcoming Piano
Indie Disco
Ballsy Rock
Design Grove
Vinylhits
Pulsing Out Score
Rainbow Rock

95 New Sound Templates Added 🎉

Liberation
Rising High
Fashion Forward
The Cheer Is Here
New Happy Vibe
Circus
Sword of Omens
Beside the Sea
Technology - Electronic
Drive To The Dream
Calm Groove
Major Winner
Octagon
Free Radical
Growing Flair
Careful Approach
Sprightly
Darbuka Song
Road Blues
Hype City Jam
Golden Moments
In The Willows
The Palace
Road To Marsaille
Hand Clap Tune
World of Wonders
Funky Lounge
Percussion Stomps
The Epic Mind
Hip-Hop Fashion
Heroic Drama
Zen Garden
Love Is All I have Got
The Evolution
O yeah
Street Orchestra
Fuego Party
Spirit Momentum
Neon Phase
Dance All Night
Organic Timelapse
Are We Alone
Future Technology
Bike Riding
Italy Classic
On My Mind
Gracious Journey
For The Happy Times
Spring Day
Green Meadow
Hopeful Future
Soiree a Illange
Oktoberfest
Sunlight
Dancing Youth
Energy of Success
No Rush
Terrace Relaxing
Traveling Together
Void Echo
Still Crazy For You
Lull Me
Keys To Joy
Gold Digger
Golden Sunrays
Holiday Sprinkles
Perfect Grind
Breakbeat Horizon
Rock and Blues
Be strong
Aspire Time
Peaceful Rising
Jazz Night
Ignite the Night
Binaural Aquamarine
Groovy Vibe
Drive
Sunny Dance
Designer Background
The Snow Is Coming
Precious Event
La Ballerina
Glass Of Rum
Like A Dream
Ragtime Rhapsody
A Time To Shine
Cool Cascade
Spring Piano
Fancy Summer
Night Waltz
Grace Is Abound
Visible
Spa Resort
The Quiet Hours
Country Heartbeat

This week we worked hard on improving our SonicSell experience based on customer feedback. All these little changes every week help us move the product forward. 💯

We also shipped a major improvement to our copy generation and we shipped stem separation.

Stem Separation

• This new addition to AudioStack's suite of audio processing tools, allows you to separate an audio file into its sound and voice components.
• Find out more in the docs! https://docs.audiostack.ai/docs/stem-separtion and https://docs.audiostack.ai/reference/separateaudio

Improvements and a lot of bug fixes

• We shipped some major improvements to copy generation in SonicSell - so your advert should now have significantly less deviations. We also added retry logic and better examples through improved prompt engineering. 💯
• 👍Update success/error toasts file uploads
• 👍SonicSell Header improvements
• 👍Remove credit-counter (users complained it was distracting)
• Powered by AudioStack is now clearer
• 🐛 Fix Workflow Inconsistencies in SideBar
• 🐛 Support special chars in files table
• 🐛 Updated copywriting to enhance the user experience

Coming soon 🚧

• We shipped some great stuff in the backend too, and we'll speak more about that next week 💯
• We also invested in our ad-serving capabilities and analytics capabilities - please reach out if you want to know more about this.