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
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