#5959th of 67 in VoiceFor voice, speech and music
mockingbird
Mandarin voice cloning toolbox built on SV2TTS
- Stars
- 36.9k
- License
- custom license
- Last commit
- Mar 2026
- Last release
- Nov 2021
- Language
- Python
36,571 on 4 Apr 202636,882 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Clones a speaker's voice from a short audio sample and synthesizes Mandarin speech from text. It reuses the pretrained SV2TTS encoder and vocoder (WaveRNN, HiFi-GAN) and needs a separately trained Tacotron-based synthesizer. Inference runs through a PyQt toolbox, a web server on port 8080, or a command-line script. The author no longer actively updates the repo.
Who it is for: Researchers and hobbyists experimenting with Mandarin voice cloning
Strengths
- Full pipeline: encoder, synthesizer and vocoder training scripts plus three inference interfaces
- Mandarin synthesizer tested on aidatatang_200zh, magicdata, aishell3 and data_aishell
- Supports both WaveRNN and HiFi-GAN vocoders
- Community-shared pretrained synthesizers are listed, so training is optional
Weaknesses
- Author says the repo is no longer actively updated; last release is 2021-11-07
- Recommended environment is old: PyTorch 1.9.0, CUDA 10.2
- Pretrained synthesizer links are on Baidu and Aliyun; some only work with version 0.0.1
- M1 Mac setup needs Rosetta and manual compilation of pyworld and ctc-segmentation
What it needs
- GPU optional
- Docker + Compose
- Needs PyTorch, ffmpeg, webrtcvad-wheels, PyQt5, visdom
- Models: SV2TTS encoder, Tacotron synthesizer, WaveRNN, HiFi-GAN
- port 8080
Quick answers
Is mockingbird open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Can you run mockingbird with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does mockingbird need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 67| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 97 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 89 out of 100 |
| 3 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 89 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 82 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 81 out of 100 |