🎉 Exciting news 🎉
Did you know you can now create your own sound template from the AudioStack platform? Simply navigate to the Content/ Resources page, upload a file and follow the instructions in the docs to create a private sound template: https://docs.audiostack.ai/docs/manage-your-content-resources
You will be able to use your sound design in any of our workflows, including SonicSell.
We'll soon be updating the production credits charged for interacting with endpoints of AudioStack API, along with AudioStack platform functionality that uses the API. These changes will result in increased pricing in some areas and decreased pricing in others, to better reflect the complexity of the functionality.
The production credits being updated are:
If you have any queries, please contact our team at [email protected].
We have added audio enhancement endpoints, added our Text Tagger to the SDK and added some security improvements and API improvements for our Voice Intelligence Layer
We are continuously working on enriching our audio capabilities so we've added the ability to evaluate, enhance and denoise audio files.
🎧 We added evaluate audio.
🎧 Enhance audio
🎧 Denoise an audio file in order to remove background noise.
💯 A quality of life improvement the Voice Intelligence Layer is now enabled if you use one of our in built tags such as <as:break>
💯 We also added improvements to the file transfer routes so you no longer need to add file names
🐛We added some security improvements for our customers to the voice preview
We've added recommendations for tags, moods and tones using the Text Tagger
See how to use them on our docs - https://docs.audiostack.ai/reference/postrecommendmoods
text = "AudioStack's technology seamlessly integrates into your product or workflow and cuts your audio production cycles to seconds while making your budgets go further."
number_of_results = 2
tags = ["happy", "fun", "valuable", "fast"]
category = "my category"
tag_item = audiostack.Content.RecommendTag.create(
text=text, number_of_results=number_of_results, tags=tags, category=category
)
print(tag_item)
mood_item = audiostack.Content.RecommendMood.create(
text=text, number_of_results=number_of_results
)
print(mood_item)
tone_item = audiostack.Content.RecommendTone.create(
text=text, number_of_results=number_of_results
)
print(tone_item)Another exciting addition to the AudioStack API - the ability to evaluate a given audio file to receive a quality evaluation, and then to enhance or denoise your audio file as needed.
We added three new endpoints as part of the Production Suite (i.e. /production/suite/), which can help you to check the quality of your recording, for example before using it for voice cloning.
With the /production/suite/enhance endpoint, you can let AudioStack do the work and both evaluate and enhance your file as needed.
Find out more in the docs:
https://docs.audiostack.ai/reference/evaluateaudio
https://docs.audiostack.ai/reference/enhanceaudio
https://docs.audiostack.ai/reference/denoiseaudio
Voice Cloner FileSize Update 📢
💯 We have shipped some improvements to the maximum file size you can upload to our file manager to clone your voice: now you can upload recordings of any file size! 🎊
These changes offer increased flexibility in uploading larger recordings for voice cloning, and this also means more natural sounding voice clones with higher audio quality outputs. Also, this optimises the processing workflow for improved efficiency. 🌈
Recommendation Endpoint
We are excited to introduce new enhancements to our recommendation endpoint, offering users an even more tailored and dynamic experience 🎊 This update focuses on providing personalized suggestions based on tone, mood, or user-specified tags.
See how to use them on our docs here, here and here
Here’s a breakdown of the key changes:
📐Recommend Tags
1️⃣ Users can now take control of their content recommendations by providing a personalized list of tags. This empowers them to fine-tune suggestions based on specific interests or preferences.
📏Recommend Tones
2️⃣ Introducing the ability to recommend the best tone from AudioStack’s curated list. Tones play a crucial role in determining the most suitable voice for your text, enhancing the overall audio experience.
🎓Recommend Moods
3️⃣ Users can now discover the perfect mood for their content with recommendations from AudioStack’s carefully curated list. Selecting the right mood is essential for finding the optimal sound design that complements the text.
🦄 These updates aim to elevate user experience by offering greater flexibility and customisation in content recommendations. Stay tuned for more exciting features and enhancements in future releases!🦄
We updated the voice cloner, where we integrated our AES (audio evaluation service) so you get a better recoded voice 💯
🐛We fixed a bug by restricting the length of organisation name
📔 Updated docs to give clearer examples of using Files as sound templates with Python SDK: https://docs.audiostack.ai/docs/custom-sound-design-templates
💯 Improvements to the UX for the AES (audio evaluation service).
💯We shipped adding sorting and filtering to media files 📁
If you log into Content/Resources in the platform, you'll see a range of sorting features to help you find your files easily.
Try it out now in our platform
🐛 Improved error messages when users hit credit limits
🚢We've shipped some improvements on the length prediction model to account for filtering out break tags and SSML tags at inference, manage negative prediction as well as empty text prediction. This results in a more accurate estimate of the duration of your produced audio!
💰We shipped improvements to the billing system, enhancing our customer experience 💯
🚤 We made significant improvements in our authentication flow in tests it was up to 10x faster so you should notice some speed improvements throughout the platform and in particular the API.
Recording Booth is in Beta 🎉You can get access to our new Recording Booth to record your voice.
If you want to test out new AudioStack features as a beta tester, please reach out to support[at]audiostack[dot]ai
