# bytedance/MegaTTS3

Repository: https://github.com/bytedance/MegaTTS3
Canonical: https://ross.abutalabs.com/products/megatts3
Language: Python
License: Apache-2.0
License Family: permissive
Topics: research
Last push: 2026-06-15T11:26:48+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 35, longevity 37
- inputs: {"age_days": 531, "days_push": 79, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6091, forks 475 (observed 2026-08-28T04:09:34.980862+00:00)

## What it is
MegaTTS 3 is ByteDance's open-source PyTorch text-to-speech model with a lightweight 0.45B-parameter Diffusion Transformer backbone. It provides high-quality zero-shot voice cloning with bilingual Chinese/English support and code-switching.

## Use cases
- clone a voice from a short audio sample
- generate speech from text in Chinese and English
- build a TTS pipeline with a lightweight model
- control accent intensity in synthesized speech
- synthesize code-switched Chinese-English speech

## When to choose
- you need high-quality zero-shot voice cloning
- you need bilingual Chinese/English TTS with code-switching
- you want a research-grade TTS model under an Apache-2.0 license

## When to avoid
- you need production TTS on Windows or macOS without extra setup
- you need many languages beyond Chinese and English
- you need fine-grained pronunciation/duration control, which is not yet implemented

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, deep-learning
- domain: speech-processing, artificial-intelligence, deep-learning
- platform: python
- tags: voice-cloning, text-to-speech, diffusion-transformer, bilingual, pytorch, zero-shot-tts, linux, gpu

## Member repositories
- bytedance/MegaTTS3 (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.980862+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 2026-08-29T17:48:17.691037+00:00, confidence not recorded.
  - readme: https://github.com/bytedance/MegaTTS3 (fetched 2026-08-28T04:09:34.980862+00:00, sha b868760ea6bc)
- Data as of 2026-08-30T08:39:29.467469+00:00.