Get started

DubVoice API

Generate speech, video, images and music through one authenticated, asynchronous API.

Base URL: https://www.dubvoice.ai/api/v1 (TTS / voices / translate / video / me) Other endpoints: https://www.dubvoice.ai/api/<feature> (image, music, edge-tts, minimax-tts).

All /api/v1/* endpoints and most other endpoints accept either of:

  • Authorization: Bearer sk_your_api_key
  • X-API-Key: sk_your_api_key

Exception: /api/video and /api/video/grok accept only Authorization: Bearer sk_your_api_key.

Generate / rotate keys at https://www.dubvoice.ai/dashboard/api-docs.

What you can build

AreaEndpointsPage
Text to speechPOST /api/v1/tts, POST /api/edge-tts, POST /api/minimax-ttsText to speech
Voices and cloningGET /api/v1/voices, POST /api/voice-cloneAccount and voices
Audio toolsPOST /api/v1/stt, /voice-changer, /dubbing, /dialogueAudio tools
TranslationPOST /api/v1/translateTranslate
VideoPOST /api/v1/video, POST /api/v1/stock-videoVideo
ImagesPOST /api/image-generateImages
MusicPOST /api/music-generateMusic

How a request works

Every generation is asynchronous. You submit a job and get an id back at once, then poll the job (or receive a webhook) until it is completed or failed. Credits are taken when the job is accepted and refunded automatically if it fails.

  1. Create an API key in the dashboard.
  2. Send the request with Authorization: Bearer sk_....
  3. Poll the status endpoint, or pass webhook_url.
  4. Download the result URL.

The whole reference is also available as one Markdown file at /llms.txt, ready to paste into an AI assistant.

Search docs

Find a page or an endpoint