# babysor/MockingBird

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

Repository: https://github.com/babysor/MockingBird
Canonical: https://ross.abutalabs.com/products/mockingbird
Language: Python
License: NOASSERTION
License Family: other
Topics: ai, speech, pytorch, deep-learning, text-to-speech, tts
Last push: 2026-03-03T14:59:58+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 8, longevity 100
- inputs: {"age_days": 1852, "days_push": 183, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 36909, forks 5185 (observed 2026-08-28T04:12:01.269102+00:00)

## What it is
MockingBird is a PyTorch-based AI voice cloning toolbox that can clone a voice from a 5-second sample and generate arbitrary speech in real time. It supports Mandarin and English, includes a GUI toolbox, and can serve results via a web server.

## Use cases
- clone a voice from a short audio sample
- generate speech in a cloned voice in real time
- run text-to-speech with a custom trained synthesizer
- serve synthesized speech through a web server
- experiment with SV2TTS voice cloning models
- generate Mandarin speech from text

## When to choose
- you need offline voice cloning with PyTorch on Windows, Linux, or M1 Mac
- you want to clone a voice from just a few seconds of audio
- you need Mandarin or English TTS with a pretrained encoder and vocoder

## When to avoid
- you need actively maintained software with up-to-date dependency support
- you want a managed cloud-hosted voice cloning service
- you need production-grade licensing clarity (license is non-standard)
- you require the latest PyTorch versions out of the box

## Facets
- artifact type: application
- maturity: maintenance
- function: tts, speech-recognition, machine-learning, deep-learning, audio-processing
- domain: speech-processing, artificial-intelligence, deep-learning
- platform: python, windows
- tags: voice-cloning, text-to-speech, pytorch, sv2tts, real-time-synthesis, mandarin, chinese, audio, linux, macos, gpu

## Member repositories
- babysor/MockingBird (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.269102+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 2026-08-29T16:25:47.617100+00:00, confidence not recorded.
  - readme: https://github.com/babysor/MockingBird (fetched 2026-08-28T04:12:01.269102+00:00, sha d97cb90622d4)
- Data as of 2026-08-30T08:39:29.467469+00:00.