{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/kyutai-pocket-tts/","md":"https://postcutoff.com/m/kyutai-pocket-tts/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"kyutai-pocket-tts","name":"Kyutai Pocket TTS","org":"Kyutai","family":"Pocket TTS","released":"2026-01-13","status":"current","type":"audio/speech","modality_in":["text","audio"],"modality_out":["audio"],"open_weights":true,"model_license":"cc-by-4.0","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face","model_id":"kyutai/pocket-tts","url":"https://huggingface.co/kyutai/pocket-tts"},{"provider":"Hugging Face (no cloning variant)","model_id":"kyutai/pocket-tts-without-voice-cloning","url":"https://huggingface.co/kyutai"},{"provider":"GitHub / pip","model_id":"pocket-tts","url":"https://github.com/kyutai-labs/pocket-tts"}],"capabilities":[{"name":"100M-param TTS with cloning, real time on CPU","detail":"~200 ms to first audio and ~6x real time on a MacBook Air M4 CPU; streaming, unbounded text length; voice cloning from audio.","first":false,"discovered":"launch","source":"https://huggingface.co/kyutai/pocket-tts"},{"name":"Six languages","detail":"English, French, German, Spanish, Portuguese, Italian (multilingual since 2026-05-04).","first":false,"discovered":"later","source":"https://kyutai.org/blog/"}],"entry":null,"notes":"Gated on HF (accept prohibited-use terms). Training code released 2026-08-25; 2026-09-28 post describes a 'drifting' objective replacing flow matching for the sampler head. `pip install pocket-tts`. Community WebAssembly ports run in-browser.","verified":"2026-09-29","body_md":"Sources: https://huggingface.co/kyutai/pocket-tts , https://github.com/kyutai-labs/pocket-tts , https://kyutai.org/blog/","page_url":"https://postcutoff.com/m/kyutai-pocket-tts/","standing":{"kind":"speech and audio","newer_count":72,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"kyutai-tts-stt","name":"Kyutai TTS 1.6B / Kyutai STT + Unmute","org":"Kyutai","released":"2025-07-03","page_url":"https://postcutoff.com/m/kyutai-tts-stt/"},"after":null,"weights":"public","licence":"cc-by-4.0","licence_permissive":false,"summary":"Weights are public. Licence: CC BY 4.0. See the licence for commercial terms."}}