FICHA · AUR

coqui-tts

Deep learning for Text to Speech

  • App
  • CLI
  • AUDIO
  • Launchable
  • Runs in terminal
official+codex · reviewed · May 31, 2026 description in en

Description

Text can be synthesized into speech with deep-learning text-to-speech models. It is useful for accessibility experiments, voice generation, narration workflows, and research around speech synthesis.

Voice models can sound realistic and may have licensing or consent limits. Review model sources and avoid generating speech that impersonates people without permission.

How to run

tts

Commands: tts

Permissions

Permissions not analysed for this source yet.