Chatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI. We are excited to introduce Chatterbox-Turbo, our most efficient model yet. Built on a streamlined 350M parameter architecture, Turbo delivers high-quality speech with less compute and VRAM than our previous models. We have also distilled the speech-token-to-mel decoder, previously a bottleneck, reducing generation from 10 steps to just one, while retaining high-fidelity audio output. Paralingu...
https://api.deepinfra.com/v1/openai/audio-speech$1.0000 per 1M input characters
| Model | Max chars | Sample rate | Voices | Languages |
|---|---|---|---|---|
| chatterbox-multilingual | — | — | — | — |
| chatterbox-turbo | — | — | — | — |
/v1/models/deepinfra/ResembleAI/chatterbox-turboChatterbox is a family of three state-of-the-art, open-source text-to-speech models by Resemble AI. We are excited to introduce Chatterbox-Turbo, our most efficient model yet. Built on a streamlined 350M parameter architecture, Turbo delivers high-quality speech with less compute and VRAM than our previous models. We have also distilled the speech-token-to-mel decoder, previously a bottleneck, reducing generation from 10 steps to just one, while retaining high-fidelity audio output. Paralingu...