# coqui-ai/TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Repository: https://github.com/coqui-ai/TTS
Canonical: https://ross.abutalabs.com/products/tts
Homepage: http://coqui.ai
Language: Python
License: MPL-2.0
License Family: copyleft
Topics: python, text-to-speech, deep-learning, speech, pytorch, tts, vocoder, tacotron, glow-tts, melgan, speaker-encoder, hifigan, speaker-encodings, multi-speaker-tts, tts-model, speech-synthesis, voice-cloning, voice-synthesis, voice-conversion
Last push: 2024-08-16T12:07:14+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2296, "days_push": 747, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 45953, forks 6146 (observed 2026-08-28T04:12:09.703974+00:00)

## What it is
Coqui TTS is a deep learning toolkit for text-to-speech synthesis, providing pretrained models in over 1100 languages plus tools for training and fine-tuning new models. It supports advanced features like multi-speaker TTS, voice cloning, and streaming inference with low latency.

## Use cases
- convert text to natural-sounding speech
- clone a voice from audio samples
- fine-tune a TTS model for a new language
- generate speech in multiple languages
- train a custom text-to-speech model
- build a voice assistant with speech output
- convert audio between speakers

## When to choose
- you need production-ready TTS with pretrained models in many languages
- you want to train or fine-tune custom speech synthesis models
- you need voice cloning or multi-speaker synthesis in Python
- you want low-latency streaming speech generation

## When to avoid
- you need a lightweight non-ML text-to-speech engine for embedded devices
- you only need simple offline system voices without deep learning
- you require active commercial support or frequent updates, as the original company shut down

## Facets
- artifact type: library
- maturity: maintenance
- function: tts, machine-learning, deep-learning, audio-processing
- domain: speech-processing, machine-learning, deep-learning
- platform: python, cross-platform
- tags: voice-cloning, speech-synthesis, vocoder, pytorch, pretrained-models, multi-speaker-tts, voice-conversion, audio, gpu

## Member repositories
- coqui-ai/TTS (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:09.703974+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:21:38.026672+00:00, confidence not recorded.
  - readme: https://github.com/coqui-ai/TTS (fetched 2026-08-28T04:12:09.703974+00:00, sha f61f1e1103b8)
  - registry_pypi: https://pypi.org/pypi/tts/json (fetched 2026-08-29T07:45:07.983035+00:00, sha ef0b93da8503)
- Data as of 2026-08-30T08:39:29.467469+00:00.