pocket-tts

Generate spoken audio from text on a CPU with Pocket TTS, a lightweight Python text-to-speech tool. Use its Python API or CLI without a GPU or speech-generation web API.

Share on XLicense: MIT

Overview

Pocket TTS is a lightweight Python text-to-speech application for generating spoken audio on CPUs, without requiring a GPU or a speech-generation web API. Install it with pip, then use its Python API or command-line interface to turn text into audio. It supports streaming output, voice cloning, and English, French, German, Portuguese, Italian, Spanish, and Dutch. It can process long text inputs.

Key features

  • Generate speech on a CPU without a GPU or speech-generation web API
  • Use a Python API or command-line interface
  • Stream audio and process long text inputs
  • Clone voices and generate speech in seven supported languages

Best for

Python developers and users who want to generate speech locally on a CPU. It is useful when a GPU or speech-generation web API is not wanted.

Upstream
kyutai-labs/pocket-tts
Fork on GitHub
Guo-astro/pocket-tts
Upstream stars
9.8k
Category
Documents, media and content
Language
Python
License
MIT
Forked
2026-10-09
Sync status
In syncLast synced 2026-10-10