Exciting news! ๐ฅณ We're delighted to unveil the latest additions to our diverse voice library โ introducing the eagerly awaited OpenAI voices. Meet them under the names alloy, echo, fable, onyx, nova, and shimmer. These voices not only boast excellent prosody, pitch, and intonation but also offer multilingual capabilities, supporting a whopping 28 languages ๐ฒ :
โGenerate spoken audio in your preferred language by providing input text in the language of your choice. Note that while optimized for English, our voices perform admirably across most of the languages mentioned aboveโ
โAs responsible synthetic voice advocates, kindly ensure clear disclosure to end-users that the TTS voice is AI-generated and not a human voiceโ
We value your feedback ๐ฏ โ share your thoughts with us!
Introducing new Ultra-Realistic AI Voices from PlayHT!
We're thrilled to announce the addition of cutting-edge AI voices to our repertoire, crafted using next-generation speech technology by PlayHT. These voices bring a new level of human-like emotion to text-to-speech generation, providing an immersive and expressive experience. These voices are English with various accents: ๐บ๐ธ American, ๐ฌ๐ง British, ๐ฆ๐บ Australian and ๐จ๐ฆCanadian. Explore the expressive range of these voices, each uniquely crafted to elevate your content across various formats. From advertisements, to podcasts to training videos, our new voices offer versatility and authenticity. Try them all out in our Library with another 1200 voices!
โค๏ธ We're committed to providing you with the latest advancements in AI voice technology, we have more state of the art AI voices coming next week โค๏ธ
Deprecation Notice ๐ข
Later this week three of our voices will be deprecated ๐ : Renata, Jollie, Matthew. If you rely on any of these voices for your audio creation, please make sure that you migrate to a new voice before the end of next week. You can find all available voices in our Library. Worry not, because we have more voices announced very soon, watch this space ๐ฏ
Many of the voice providers in our library add padding to the end of speech files by default, so that sentences don't end too suddenly. There are some situations where users have reported needing to remove this padding so that they can specify a more precise, consistent amount of padding across different voices and providers. This is now possible using /speech/tts/remove_silence.
M4A Encoding
๐ AudioStack now supports M4A encoding. Simply specify "m4a" as the preset to use this feature.
Javascript SDK Quickstart
We added a quick start guide to get Javascript developers up and running using our SDK. You can find it here.
If you have any feedback about our documentation or would like to request docs on specific workflows, please get in touch at [email protected].