VoiceStudio by Palash Debnath (Yupcha Softwares)

agent.md for AI agents

Local desktop app for voice cloning, voice design, video dubbing, dictation and transcription in 646 languages, with a local API and an MCP server for agents.

Voiceover (text-to-speech) Open source

Is VoiceStudio free for commercial use? Yes with conditions →

Website License API docs Pricing

Price

Free

The AGPL-3.0 app is free and runs on your own hardware...

Commercial use

With conditions

AGPL-3.0 (app); default OmniVoice weights CC-BY-NC

Credit the author

Per item

Credit depends on the item

Agent access

Official MCP server

no key needed

AgentGid articles about VoiceStudio

All guides

VoiceStudio: The Free, Local ElevenLabs Alternative, Checked

A viral post calls VoiceStudio a 100% free ElevenLabs replacement with 19.4K stars. We checked it against GitHub and the project's own pages: what it does, what is really free, the license catch in the default voice model, and how to plug it into Claude Code or Codex.

Read the article · 6 min →

VoiceStudio popularity

Gid Score

56 /100

same scale as developer tools

GitHub stars

79.3K

8,718 forks · debpalash/VoiceStudio

Downloads

—

PyPI, last 7 days, None

VoiceStudio: GitHub starsdebpalash/VoiceStudio 79,301

Downloads from the package registry, stars and forks from GitHub, checked Oct 21, 2026. How the Gid Score is calculated.

Rules for your agent

- VoiceStudio (Voiceover (text-to-speech)). Local desktop app for voice cloning, voice design, video dubbing, dictation and transcription in 646 languages, with a local API and an MCP server for agents. Price: free; commercial use with conditions; credit depends on the item; ship inside your app with conditions.
  Connect: official MCP server http://localhost:3900/mcp/; API docs https://github.com/debpalash/VoiceStudio/blob/main/docs/speech-platform.md. Limits: Local: limited only by your hardware.
  Get files: Local desktop app: API at http://127.0.0.1:3900 (capabilities at GET /.well-known/voicestudio-speech); MCP over HTTP at POST /mcp/ or stdio via python -m backend.mcp_shim.
  Not allowed: App is AGPL-3.0: a modified version offered over a network must give users its source.
  Not allowed: Model weights keep their own terms; the default OmniVoice weights are CC-BY-NC.
  Not allowed: A separate paid commercial license exists for closed-source embedding.
  Rule: The app is AGPL-3.0: commercial and internal use are allowed, but a modified version offered over a network must ship its source.
  Rule: Model weights keep their own terms: the default k2-fsa/OmniVoice pretrained model is CC-BY-NC (non-commercial).
  Rule: Clone voices only with permission.
  License: https://github.com/debpalash/VoiceStudio/blob/main/LICENSE-NOTICE.md (checked 2026-10-17; details: https://agentgid.com/assets/voicestudio/)

Paste it into your prompt or AGENTS.md. It is built from the license and API terms below.

License

License	AGPL-3.0 (app); default OmniVoice weights CC-BY-NC
Commercial use	Commercial use with conditions “Commercial use under the AGPL-3.0 is free.” github.com/debpalash/VoiceStudio/blob/main/LI...
Credit	Credit depends on the item “Model weights, tokenizers, and other third-party assets retain their own terms.” github.com/debpalash/VoiceStudio/blob/main/LI...
Inside your app or game	Ship inside your app with conditions “the complete corresponding source code of your modified version” github.com/debpalash/VoiceStudio/blob/main/LI...
Monetized YouTube	Monetized YouTube with conditions
AI training	Not stated
Bots and bulk downloads	Not stated
Rules	The app is AGPL-3.0: commercial and internal use are allowed, but a modified version offered over a network must ship its source. Model weights keep their own terms: the default k2-fsa/OmniVoice pretrained model is CC-BY-NC (non-commercial). Clone voices only with permission.

Connect it to an agent

How an agent gets files	Local desktop app: API at http://127.0.0.1:3900 (capabilities at GET /.well-known/voicestudio-speech); MCP over HTTP at POST /mcp/ or stdio via python -m backend.mcp_shim. · no sign-in
Not allowed	App is AGPL-3.0: a modified version offered over a network must give users its source. Model weights keep their own terms; the default OmniVoice weights are CC-BY-NC. A separate paid commercial license exists for closed-source embedding.
MCP server	Official: `http://localhost:3900/mcp/`
API	API docs · no key
Limits	Local: limited only by your hardware.
GitHub	debpalash/VoiceStudio

Pricing

Free	The AGPL-3.0 app is free and runs on your own hardware (CUDA, Apple Silicon or CPU).
Paid from	—
Usage price	Optional Pro build (Commercial License, closed source): $99 per user a year or $299 once.
Good to know	LICENSE-NOTICE: 'Commercial use under the AGPL-3.0 is free'; the paid Commercial License is for closed-source embedding and the Pro build. OmniVoice model card: 'The pre-trained model is licensed under the CC-BY-NC due to constraints from its training data'. Other engines (CosyVoice 3, IndexTTS 2.5, KittenTTS and more) can be chosen in the app, each with its own terms. MCP tools: generate_speech, clone_voice, design_voice, transcribe and more.

Sources

Read on Oct 17, 2026: github.com/debpalash/VoiceStudio, github.com/debpalash/VoiceStudio/blob/main/LICENSE-NOTICE.md, github.com/debpalash/VoiceStudio/blob/main/docs/mcp.md, github.com/debpalash/VoiceStudio/blob/main/docs/speech-pl..., huggingface.co/k2-fsa/OmniVoice, voicestudio.sh/pro.

Not confirmed: Commercial terms of the other engines' weights; output rights for generated audio with the default model beyond the CC-BY-NC note.

Not legal advice. Check the license page before you ship.

Alternatives to VoiceStudio

All voiceover (text-to-speech)

Source	Price	License	Monetized YouTube	Agent access
Cartesia Sonic Sonic TTS API (Sonic 3.6 claims 44 languages) with instant and pro voice cloning. agent.md	Free tier · from $5/mo	Commercial: conditions No bots	With conditions	MCP API `@cartesia/cartesia-js`
ElevenLabs Text-to-speech and voice cloning API in many languages, with an official MCP server. Used in 7 AI-agent projects (0.4% of Python) agent.md	Free tier · from $6/mo	Commercial: conditions No AI training No bots	With conditions	MCP API `@elevenlabs/elevenlabs-js`
Fish Audio TTS app and pay-as-you-go API priced per UTF-8 byte; S2.1-Pro claims 83 languages. agent.md	Free tier · from $11/mo	Commercial: conditions No AI training No bots	With conditions	MCP API `fish-audio-sdk`
Hume Octave Octave TTS with voice cloning and an official MCP server. agent.md	Free tier · from $3/mo	Commercial: conditions No bots	With conditions	MCP API `hume`
Murf API Murf Falcon 2 TTS API at 1 cent per 1,000 characters, with an official MCP server. agent.md	Free tier · from $19/mo	Commercial: conditions No AI training No bots	With conditions	MCP API `murf`
Amazon Polly AWS text-to-speech with Standard, Neural, Long-Form and Generative voices. agent.md	Free tier	Commercial OK No credit	Yes	API `@aws-sdk/client-polly`
Azure AI Speech (Text to Speech) Azure neural text-to-speech with HD voices, long audio and Limited Access custom voices. agent.md	Free tier	Commercial: conditions	With conditions	API `microsoft-cognitiveservices-speech-sdk`
Deepgram Aura Aura-2 text-to-speech API priced per 1,000 characters. Used in 3 AI-agent projects (0.1% of JS) agent.md	Free tier	Commercial: conditions No AI training No bots	Unclear	API `@deepgram/sdk`