Pocket TTS
Pocket TTSv100MCurrentReleased January 13, 2026
Context1M tokens
Training CutoffNot disclosed
CategoryAudio Model
About Pocket TTS
Pocket TTS is a lightweight text-to-speech model and Python package from Kyutai Labs designed to run efficiently on CPUs with streaming, low-latency audio generation.
Capabilities
text to speechaudiovoice cloningmultilinguallocal inference
Input Modalities
text
Output Modalities
audio
Technical Details
- API Identifier
- kyutai/pocket-tts
- Category
- Audio Model
- Context Window
- 1,000,000 tokens
Tags
text-to-speechaudio-modelcpu-inferencevoice-cloningopen-sourcekyutai
Run this model yourself
Local and cloud setup for Pocket TTS, with exact configurations, sources and clear evidence limits.
No reviewed setup guide is available for this model yet. Explore configurations with documented support in the hardware finder.
Pricing and access
Open-source/local model; no hosted API price is listed in the source repository. Compute costs depend on user hardware.
Kyutaiai lab
Open-science speech and audio AI research lab
1 ModelsFounded 2023Paris, France
View full profile