1. Create an account

Sign up free, verify your email, and use the JWT returned by login.

2. Authenticate

Add your JWT to the Authorization header:

Authorization: Bearer <your_access_token>

3. Generate Speech

POST to synthesize. Send text, voice, and params:

curl -X POST https://duramolab.com/api/v1/tts/synthesize/ \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: one-key-per-client-request" \
  -d '{
    "text": "Hello, welcome to Duramo Lab!",
    "voice_id": "Dennis",
    "speed": 1.0
  }'

4. Poll for Result

The response returns an id. Poll the status endpoint until it is done:

GET /api/v1/tts/history/<id>/status/

Authentication

• POST /api/v1/auth/login/— Obtain JWT tokens
• POST /api/v1/auth/register/— Create a new account
• POST /api/v1/auth/refresh/— Refresh your JWT token
• GET /api/v1/auth/profile/— Get account and usage info

Text to Speech

• POST /api/v1/tts/synthesize/— Submit text for speech synthesis
• GET /api/v1/tts/history/<id>/status/— Poll synthesis status
• GET /api/v1/tts/history/— View your synthesis history
• GET /api/v1/voices/— List available voices

Voice Cloning

• POST /api/v1/voices/upload/— Upload audio to clone a voice
• GET /api/v1/voices/— List your cloned voices
• DELETE /api/v1/voices/<id>/— Delete a cloned voice

Projects & Billing

• GET /api/v1/projects/— List your projects
• POST /api/v1/projects/— Create a new project
• GET /api/v1/subscription-plans/— View available plans