Local, offline Python toolkit that combines speech-to-text, text-to-speech, voice cloning and conversion, music generation, and audio cleanup in one CLI and GUI.
52392PythonAGPL-3.0Updated 19 days ago
leemysw/yovoice
Local, offline desktop studio for macOS and Windows that turns text into speech, clones voices, and generates songs with lyrics and MIDI scores.
Open-source alternative to:ElevenLabs
Suno
- Stars
- 1,694
- Forks
- 128
- Open issues
- 13
- Last commit
- yesterday
What is it?
yovoice is an open-source desktop app for creating speech, songs and multi-track scores on your own computer. It covers text-to-speech with voice design and cloning, emotion and delivery controls, story dubbing where each line can be assigned to a character, and AI music generation from style prompts and lyrics. Generation runs locally on CPU or GPU with no cloud API calls, and the app ships with bundled inference runtimes for Windows CUDA and macOS Metal.
The Score module lets you write parts by bar and beat, import MIDI, render with a General MIDI sound font, and export MIDI and stems. Creators can keep multiple takes for side-by-side comparison, trim waveforms and export clean stems or MIDI files.
Beyond the desktop UI, yovoice provides a standalone CLI, an authenticated HTTP API and an MCP server so agents such as Cursor or Claude Code can drive generation. An optional built-in assistant can connect to DeepSeek, Qwen, OpenAI, Anthropic or Ollama, with API keys kept on the local machine.
Key features
- 01Zero-shot voice cloning and voice design from a text description
- 02Story dubbing with per-line character assignment and subtitle import
- 03AI song and instrumental generation from style prompts and lyrics
- 04Score editor with MIDI import and General MIDI rendering
- 05Local CLI, authenticated HTTP API and MCP server for agent integration
- 06Interface available in 12 languages
Use cases
- Narrating articles or scripts locally without per-character cloud fees
- Cloning a reference voice for consistent voiceovers
- Drafting songs from lyrics and arranging MIDI parts
- Letting a coding agent generate speech files from the command line
Quick start
- 1
Download the package for your platform from Releases or the official website
- 2
Install the app (macOS: drag to Applications; Windows: run the setup installer)
- 3
Download a model in Settings, then create a project and generate audio
- 4
For development, install dependencies and run the app
make install make app-run
Things to know
- Desktop app only for macOS 14+ on Apple Silicon and Windows 10/11 x64; no Linux support is listed.
- Some models (OmniVoice, YuE2, Breeze TTS 2) are restricted to non-commercial use.
- Models must be downloaded separately, and some require substantial hardware such as a GPU for good performance.
Topics
FAQ
- What is yovoice?
- Local, offline desktop studio for macOS and Windows that turns text into speech, clones voices, and generates songs with lyrics and MIDI scores. yovoice is an open-source desktop app for creating speech, songs and multi-track scores on your own computer. It covers text-to-speech with voice design and cloning, emotion and delivery controls, story dubbing where each line can be assigned to a character, and AI music generation from style prompts and lyrics. Generation runs locally on CPU or GPU with no cloud API calls, and the app ships with bundled inference runtimes for Windows CUDA and macOS Metal.
- Is yovoice free to use? What license does it have?
- yovoice is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is yovoice still maintained?
- Actively maintained. The last commit to yovoice was on Oct 19, 2026.
- What can I use yovoice for?
- Narrating articles or scripts locally without per-character cloud fees Cloning a reference voice for consistent voiceovers Drafting songs from lyrics and arranging MIDI parts Letting a coding agent generate speech files from the command line
- How do I install yovoice?
- Download the package for your platform from Releases or the official website Install the app (macOS: drag to Applications; Windows: run the setup installer) Download a model in Settings, then create a project and generate audio For development, install dependencies and run the app: make install make app-run
- Where can I get yovoice?
- The source code and installation instructions are on GitHub: https://github.com/leemysw/yovoice
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source text-to-speech system with voice cloning, natural-language emotion control and multi-speaker generation, built on LLM-style models.
33.3K2.9KPythonOtherUpdated 6 days ago
Open-source text-to-speech model family by Resemble AI, with voice cloning from a short reference clip across English and many other languages.
27.1K3.6KPythonMITUpdated 3 months ago
Open-source text-to-speech library whose KittenTTS 2 model clones voices from 5 seconds of audio and runs in real time on a CPU.
16.2K967PythonApache-2.0Updated 4 days ago
A desktop app for building AI digital humans, with lip-sync video synthesis, text-to-speech, voice cloning, and local AI model management.
5.7K840VueApache-2.0Updated 6 hours ago
Lightweight zipvoice-based TTS model for voice cloning and 48kHz speech generation, running at over 150x realtime on GPU.
5.5K685PythonApache-2.0Updated 5 months ago