APIUp to 25% cheaper than official pricesTry the API →
Hermes
APIModelsCases
Back to News
newsAudioOpen Source

Kyutai Opens Pocket TTS Training So Anyone Can Build CPU Voice Cloning

Kyutai released the full training stack for its 100M-parameter Pocket TTS, letting anyone train a voice model from scratch for under $200.

Kyutai Opens Pocket TTS Training So Anyone Can Build CPU Voice Cloning
Source
kyutai
Published
Author
AlphaSignal Newsroom
Read
1 min read

Kyutai released the full training stack for its 100M-parameter Pocket TTS, letting anyone train a voice model from scratch for under $200.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

Meta's AudioCraft Adds JASCO and MusicGen-Style for Precise Music Control
AlphaSignal · repo

Meta's AudioCraft Adds JASCO and MusicGen-Style for Precise Music Control

Meta's Omnilingual ASR Brings Speech Recognition to 1,600 Languages
AI at Meta · news

Meta's Omnilingual ASR Brings Speech Recognition to 1,600 Languages

MOSS-Music Beats Gemini on Music AI and Now Runs Locally
AlphaSignal · model

MOSS-Music Beats Gemini on Music AI and Now Runs Locally