OpenAI compatible
Use the OpenAI SDK and change the base URL.
Local API
A local API that speaks OpenAI
Turn on the built-in server and generate speech from Python, Node, n8n or anything that can send an HTTP request. Apps built for OpenAI text to speech work by changing one URL.
Available on: Pro
curl -X POST http://127.0.0.1:7860/api/v1/voice-clone \ -H "X-API-Key: $KEY" \ -H "Content-Type: application/json" \ -d '{"text": "Hello!", "voice": "My Voice"}' \ --output hello.wav
What you get
Built for real work
Every engine
List models, load them and generate with any engine you have installed.
Streaming and formats
WAV, raw PCM or base64 JSON, with streaming output.
Private by default
API-key protected and listening on 127.0.0.1 only, while the app is open.
How it works
In 3 steps
1
Turn it on
Open Settings, then API Server, and start the server.
2
Copy your key
Each installation has its own key.
3
Send a request
Use the docs or the OpenAPI spec.
FAQ
Common questions
Does the API work without the app?
No. The app must be open, and your program must run on the same computer.
Is the API on the free plan?
No. It needs an active license.
Try Local API on your own computer
Install Musa TTS free. Upgrade only when you need more.