KyutaiKyutai TTS
Kyutai TTS 1.6B English/French
Kyutai TTS 1.6B English/French converts a stream of text into speech. It belongs to Kyutai's Delayed Streams Modeling family and can begin producing sound before all text has arrived.
Research release
The release has its own audio configuration
The bilingual model generates 32 audio tokens per frame. Applications can use fewer tokens to trade audio quality for speed. The model supports voice conditioning.tts-1.6b-en_fr: Kyutai model card
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | kyutai/tts-1.6b-en_fr |
| Parameters | The card reports about 1.8B parameters, despite the 1.6B release name.tts-1.6b-en_fr: Kyutai model card |
| Weight license | CC BY 4.0.tts-1.6b-en_fr: Kyutai model card |
| Text/audio offset | 16 frames, equivalent to 1.28 seconds at 12.5 frames per second.tts-1.6b-en_fr: Kyutai model card |
Related models
A streaming neural audio codec that compresses speech into tokens and reconstructs sound from them.
Launch date not confirmedResearch releaseDownloadable