kyutai-labs/pocket-tts
- Source
- GitHub
- First trending
- Category
- Media
- GitHub stars
- 9,539
- Main language
- Python
This page introduces an external open-source repository. It is not an HDATF product.

What it does
A small text-to-speech model that runs on a CPU without needing a GPU, with streaming audio, voice cloning, a Python API and a CLI. It supports English, French, German, Portuguese, Italian and Spanish, and can run in a browser.
How it helps ATF
Only loosely related to our products. It could be a reference for speech output on ordinary PCs without a GPU, such as reading documents aloud in a workspace like ATF Works.
License
MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.
More in this category
- originalankur/maptoposter
A Python script that creates and exports minimalist map posters for cities, with a choice of themes such as blueprint or japanese_ink. - chatfire-AI/huobao-drama
A full-stack platform that automates short drama production. LLMs parse scripts to extract characters, scenes and storyboards, then image and video models produce designs and clips that are composited into episodes. - torvalds/AudioNoise
AudioNoise is a set of simple digital audio effects, such as phaser and echo, written to learn the basics of audio processing. It uses IIR filters and delay loops that take one sample in and give one out. - cjpais/Handy
A cross-platform desktop app for offline speech-to-text. You hold or tap a shortcut, speak, and the transcribed text is pasted into the active app, with Silero VAD filtering silence and local Whisper or Parakeet models transcribing. - remotion-dev/remotion
A framework for making videos with React code, where the code is the source of truth. Videos can be made with a coding agent, edited by drag and drop, or tied to data and batch-rendered on your own infrastructure.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.