450 NEW VOICES ADDED 🎉

• We added 450+ new voices to the Voice Library
• Including some new voices such as Nivedita which is a Malayalam 🇮🇳 voice.
• We also added some new voices from 🇰🇷, 🇳🇴, 🇧🇷 and many more!
• You can check them out here https://library.audiostack.ai/
• Let us know at [email protected] what your favourite voice is for the chance to win a prize! 📥

Platform Improvements [beta]

We added AdLocal to the Beta in https://platform.audiostack.ai

This enables you to run localised national radio or podcast campaigns.

A screenshot of some of the options 💯

Bug Fix - Voice Intelligence layer

• Our customers reported a 🐛 where the dictionary was incorrectly updated, this turned out to be an edge case involving some ~being passed into one of our systems. Well done to the engineering team for hunting this one down, this was a hard one! 🎩
• We are constantly working on bug fixes and improvements to our systems.

Improved Incident Response Systems ⏰

• We invested heavily this week in improving our internal alerting systems - this is to further enhance our reliability. The improvements were rolled out this week 💯

 Voice Intelligence Layer Quality Enhancements

• We added 2500 tests to our continuous integration system, enhancing the quality of our product and the customer experience.

A Couple More Layered Sound Templates... [beta]

• We've made sound layering available for the following templates:ambient_electronica, eighties_chill
• These now have intense, soft and default intensity options. For more information about the layered sound template beta, see our previous ChangeLog post.

Sound Template Intensity (Beta feature)

• New feature allows you to specify how intense you would like a specific sound template to sound, changing the "timbre" of the sound design.
• For example, a more intense sound template might include heavier percussion and more complex melodies. A soft version of the template might sound more sparse, with just melodic instruments and chords, for example.
• To use this feature, you need to specify which of the "soundLayers" to use in the mix: choose from soft, intense, or default.
• This feature can currently be used with two supported sound templates: chromatic_jazz and friendly_electronica.

import audiostack
import os

audiostack.api_key = "APIKEY"
audiostack.api_base = "https://v2.api.audio"

print(audiostack.Production.Mix.list_presets())

scriptText2 = """
<as:section name="intro" soundSegment="intro">
Insert your script for the intro section here
</as:section>

<as:section name="main" soundSegment="main">
And this is the main section!
</as:section>

<as:section name="outro" soundSegment="outro">
Here is your outro.
</as:section>
"""


script = audiostack.Content.Script.create(scriptText=scriptText2)
print("response from creating script", script.response)
scriptId = script.scriptId

# create one tts resource
tts = audiostack.Speech.TTS.create(scriptItem=script, voice="bryer")
print(tts.speechId)

sound_template = "chromatic_jazz"
sound_layer = "intense"
mix = audiostack.Production.Mix.create(speechItem=tts, soundTemplate=sound_template, masteringPreset="musicenhanced", soundLayer=sound_layer)# sectionProperties={"main" : {"endAt" : 120}})
print(mix)


encoded = audiostack.Delivery.Encoder.encode_mix(productionItem=mix, preset="wav")
encoded.download(fileName=f"{sound_template}_{sound_layer}")

👍

We love to receive feedback about beta features

If you have any thoughts on this feature, please get in touch at [email protected].

We'll be launching a more extended version of this feature which supports lots more sound templates soon.

Mastering Improvement

• We added MP3 support for media files in mastering - this means you can upload MP3 media files and include them in your final asset

🚧

Don't forget to update the SDK to access new features

In Python, you can do this by running the command pip3 install -U audiostack

Bug fixes and code quality enhancements

• Bug fix for joining speech files back together when there was an error, customer facing bug
• We improved the code quality in one of our core services improving your customer experience
• New SDK version https://pypi.org/project/audiostack/

 Platform update

• New features in Platform. Save audio assets locally, so that your session is saved, improving the customer experience.

New mastering preset 🎉

• We added a "voice only" preset (mastering engine feature) 💯
• By using this preset, mastering will only applied to the generated voice and not the sound design beneath it. This is perfect for cases where you've already applied mastering to the sound template (or received a finished advert that you want to add an audio tag to).

Code Example:

mix = audiostack.Production.Mix.create(
    speechItem=tts,
    soundTemplate="pulsing_guitar",
    masteringPreset="voiceonly",
)

Docs

• We added a new guide, with code example, to support workflows where users need to add an audio "tag" to the end of an existing audio advert: <https://docs.audiostack.ai/docs/advanced-timing-example-add-a-tag-to-the-end-of-an-advert>

Terms of use and Legal

• Updated our terms of use - https://audiostack.ai/terms-of-use to make the licence terms of our sound templates clearer and easier to understand.

Sound templates

• New sound templates live. We added 14 more templates, covering a range of genres and styles.
• You can see a full list of our templates here: https://docs.audiostack.ai/docs/sound-templates-and-sound-designs

Speech / Predict

• We've added a new endpoint which draws on 4 million data points to predict the duration of speech from a given script and list of voice names 🤓
• This will allow users to determine whether a voice is suitable, or whether their script is the correct length for their project, without needing to generate the audio itself, saving time and credits! ⏰
• Find out more and check out a code example in our guide, in the API reference or in the video below 👇

📢 We've added documentation and code examples on how to generate an audio "tag" and add it to the end of an existing audio advert. Find out more here.

Sound Templates

Sound template terms of use have been added for free and paying customers - we can now refer to the terms of use if people have questions about how they are allowed to use our templates.

You can refer here - https://audiostack.ai/terms-of-use

 Security updates

📘

Security updates

This doesn't mean that our old API was insecure, we're committed to updating and reducing any risks of compromise to our customers. We regularly review security updates, and we regularly patch any found errors.

We did a range of fixes to cover some security issues. These include

• https://nvd.nist.gov/vuln/detail/CVE-2022-25901
• https://nvd.nist.gov/vuln/detail/CVE-2022-25860
• https://nvd.nist.gov/vuln/detail/CVE-2021-44906
• https://nvd.nist.gov/vuln/detail/CVE-2023-26115

We are continuously working on these improvements and also decommissioned some older parts of our API as well.

Voice Playground (Platform) - Beta 🚧

• New workflow which is the replacement for the simple frontend we previously had in the example frontends
• A few small UI improvements and new sound library will come next week
• See it at http://platform.audiostack.ai

New Voice Library

• Updated the design
• Fixed provider names
• Is completely reusable and can be accessed at: http://library.audiostack.ai in the platform as a standalone workflow with the ability to preview, and in the voice select modal in the voice playground and sonic sell

SSML Prosody

We added the following functionality to have better prosody across providers. , ,

import audiostack


audiostack.api_key = "APIKEY"

text = """ The following part should be <as:prosody pitch="x-high" rate="x-fast" volume="x-loud">higher, faster and louder</as:prosody>,   
           """ 

script = audiostack.Content.Script.create(scriptText=text)
print(script.message, script.scriptId)
tts = audiostack.Speech.TTS.create(scriptItem=script, voice="henry", voiceIntelligence=True)
print(tts)
item = audiostack.Speech.TTS.get(tts.speechId)
item.download()           

Support for ElevenLabs v2 Multilingual Voices

You can now access v2 of ElevenLabs' multilingual voices via AudioStack, a major improvement in terms of improving content accessibility through language localisation. 🎉

Find out more about the capabilities of v2 on ElevenLabs' website.

We are changing the way we're providing sound templates to make it simpler for end users. Going forward, we're making it easier to understand what rights you have over the content you're working with, as we move towards offering a range of exclusive PRO-free sound templates (public rights organization free), which means that users can use the content accessed much more flexibly and with fewer restrictions.

More content is coming in the next few weeks, but while we move forward with this some of our old demo content, which had much more restrictive usage conditions, will be unavailable. If there's a sound template you really like and would like to use something similar for a broadcast ad or in a commercial setting, let us know and we will make sure we include a sound template that meets your needs.

Find out more about the sound templates we have available here:

<https://docs.audiostack.ai/docs/use-sound-templates>

Workflow Quick Start Guides

New quick start guides are now available in the AudioStack Docs, covering some of our users' most common workflows. You can find guides on:

• Creating an AI podcast and publish it using Julep
• Adding an AI voice-over to a video
• Using Dynamic Creative Optimisation to tailor audio ads to a specific customer

Are there other guides you'd like to see? Let us know in the discussion!