What is recorded here?
Conditions a consistency-model sampler on transformer context to generate continuous audio-VAE frames; the expanded2026account distills a313M teacher into a six-layer Pocket TTS backbone while retaining its sampling head.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Original2025method and expanded2026PocketTTS account bundled, not two achievements. Inherits MAR, consistency models and later Lagrangian self-distillation; audioVAE remains lossy and temperature heuristic. Expanded paper uses90Mgenerator plus decoder for advertised100M, not the whole20MVAE. CPU results are hardware-specific, not WRS reproduction; LibriSpeech evaluation uses enhanced audio for all compared baselines, and lowest WER is tied. First2equal in v3; later multilingual/training-code releases not backdated.
Read the original work
- Continuous Audio Language Models
- Kyutai scientific publications index
- Continuous Audio Language Models — expanded Pocket TTS account
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Simon Rouard; Manu Orsini; Axel Roebel; Neil Zeghidour; Alexandre Défossez
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
CALM and Pocket TTS: continuous-latent audio modeling and compact CPU distillation
Conditions a consistency-model sampler on transformer context to generate continuous audio-VAE frames; the expanded2026account distills a313M teacher into a six-layer Pocket TTS backbone while retaining its sampling head.
Scientific scope
Original2025method and expanded2026PocketTTS account bundled, not two achievements. Inherits MAR, consistency models and later Lagrangian self-distillation; audioVAE remains lossy and temperature heuristic. Expanded paper uses90Mgenerator plus decoder for advertised100M, not the whole20MVAE. CPU results are hardware-specific, not WRS reproduction; LibriSpeech evaluation uses enhanced audio for all compared baselines, and lowest WER is tied. First2equal in v3; later multilingual/training-code releases not backdated.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Simon Rouard; Manu Orsini; Axel Roebel; Neil Zeghidour; Alexandre Défossez
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.