KyutaiPocket TTS

Pocket TTS English 24-layer 2026-09

Pocket TTS English 24-layer 2026-09 is a downloadable text-to-speech checkpoint in the Pocket TTS family. Its official configuration identifies the trained weights and the components needed to generate english speech.

The configuration identifies this release

The configuration selects a dedicated english weight path with 24 backbone layers. It also names a separate package without voice cloning. Those access variants should not be confused with the language or architecture of the model.Pocket TTS english_2026-09_24l: official release configuration

Specifications & access

Pocket TTS English 24-layer 2026-09 specifications
DetailValue and conditions
AccessDownloadable
Model identifierspocket-tts:english_2026-09_24lkyutai/pocket-tts/languages/english_2026-09_24lkyutai/pocket-tts-without-voice-cloning/languages/english_2026-09_24l
Backbone depth24 transformer layers.Pocket TTS english_2026-09_24l: official release configuration
Weight licenseCC BY 4.0.pocket-tts-without-voice-cloning: Kyutai model card
Voice-cloning weightsRepository acceptance required.pocket-tts: Kyutai model card

Related models

  • An October 2026 English speech checkpoint that retrains September revision 2 with a corrected training loader.

    Launch date not confirmedDownloadable