Jul 10, 05:53 PM

OpenAI Adds TTS API with Six Voices to Playground

OpenAI has introduced a new feature in its Playground, allowing developers to easily create text-to-speech (TTS) audio content using the TTS API. The API now supports six preset voices: Alloy, Nova, Onyx, Fable, Echo, and Shimmer. This addition aims to simplify the process of generating and downloading audio versions of any text. The development marks OpenAI's entry into the voice AI development space, although some users are still awaiting the release of GPT-4's audio-to-audio capabilities.

#OpenAI #Playground #Alloy #Nova #Onyx #Fable #Echo #Shimmer

Written with ChatGPT (GPT-4o).

Sources

TestingCatalog News 🗞@testingcatalog
2 years ago
Now you can give a try to more pre-made voices from @OpenAI on the new TTS Playground. There you can generate and download an audio version of any text with the latest OpenAI TTS API. - Alloy - Nova - Onyx - Fable - Echo - Shimmer Will we see them on ChatGPT eventually? 🤷 https://t.co/bgfIeDGcB1
Shaun Ralston@shaunralston
2 years ago
🔊 Devs! Log into #Playground for an even easier way to create TTS audio content #API 🎉 https://t.co/LiZakaO36b
AshutoshShrivastava@ai_for_success
2 years ago
OpenAI text-to-speech is now available in Playground! https://t.co/99f0XEzU9D

OpenAI Adds TTS API with Six Voices to Playground

Sources

Additional media