KyutaiKyutai STT
Kyutai STT 1B English/French
Kyutai STT 1B English/French transcribes incoming speech while audio is still arriving. It uses the Delayed Streams Modeling approach and produces text with a configured delay instead of waiting for a complete recording.
Research release
The model is designed for a live audio stream
The smaller bilingual model provides a lower configured output delay than the English-only 2.6B release. Its semantic voice activity signal helps applications identify speech activity. Candle, MLX and Transformers packages are deployment forms of the same release.stt-1b-en_fr: Kyutai model card
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | kyutai/stt-1b-en_frkyutai/stt-1b-en_fr-candlekyutai/stt-1b-en_fr-mlxkyutai/stt-1b-en_fr-trfs |
| Languages | English and French.stt-1b-en_fr: Kyutai model card |
| Model delay | 0.5 seconds; this is not a full application response-time guarantee.stt-1b-en_fr: Kyutai model card |
| Weight license | CC BY 4.0.stt-1b-en_fr: Kyutai model card |
Related models
- Kyutai STT 2.6B English
Kyutai ยท Kyutai STT
A streaming English transcription model with a configured output delay of 2.5 seconds.
Launch date not confirmedResearch releaseDownloadable