Tortoise TTS is an open-source text-to-speech using GPT-3 like techniques for creating speech models, and generates comparable quality to all recently launched text-to-speech products. We built an open-sourced at-cost pay-per-second API for it.
Hi, I'm Vatsal, one of the builders of this project.
The quality of intonation Tortoise TTS (an open-source model) generates is unparalleled, and we wanted to make this technology accessible to everyone. So, we built an open-source, at cost, pay per second API for Tortoise TTS.
Running Tortoise now requires a single API call - it costs $0.03/query. The WAV file is downloadable, we apply no restrictions.
We're trying to improve the open-source model in the background, and have already improved its speed by 30% from the original code.
All our work is open-source, and you can find all the details at: https://twitter.com/vatsal_aggar... , and try it out at : https://tts.themetavoice.xyz
clip.audio