KyutaiPocket TTS

Pocket TTS English 2026-10

Pocket TTS English 2026-10 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

This October checkpoint retrains the September revision-2 recipe with a training-loader correction. The default english configuration points to these same weights; it is an alias, not another model.Pocket TTS english_2026-10: official release configuration

Specifications & access

Pocket TTS English 2026-10 specifications
DetailValue and conditions
AccessDownloadable
Model identifierspocket-tts:english_2026-10kyutai/pocket-tts/languages/english_2026-10kyutai/pocket-tts-without-voice-cloning/languages/english_2026-10pocket-tts:english
Backbone depth6 transformer layers.Pocket TTS english_2026-10: 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 18.2M-parameter distilled English speech model with an eight-layer backbone and a reduced decoder.

    Launch date not confirmedDownloadable