Live Phone is generally available. Other product docs below remain Preview unless marked Live; endpoints and fields on Preview products may change.

VoxVain docs

VoxVain is one API for text to speech, speech to text, turn detection, real-time voice agents and phone. Phone is generally available. Text to speech is specified in the OpenAPI document. Other products remain Preview placeholders unless marked Live.

Product guides

Guides for each product are on their way. Each link below opens a placeholder until its guide is published.

Quickstart

  1. Get an API key

    See API keys below. Export it so the examples can read it:

    export VOXVAIN_API_KEY="your-key-here"
  2. Make some speech

    Send text and a voice id. The response is audio, not JSON.

    Preview API
    curl -X POST https://api.voxvain.com/v1/text-to-speech/aria \
      -H "Authorization: Bearer $VOXVAIN_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{"text": "Hello from VoxVain.", "output_format": "mp3"}' \
      --output hello.mp3
  3. List voices

    GET /v1/voices returns the ids you can pass in that path. Usage for the key is GET /v1/usage.

API keys

Get a free API key with just your email. It is issued straight away, no card and no approval step. It is shown once, so copy it then. Upgrade to Pro or Scale on Pricing.

  • Send the key as Authorization: Bearer … on every request.
  • Keep it on your server. Never put it in browser or mobile code.
  • Store it in the VOXVAIN_API_KEY environment variable, not in source control.

SDKs

There is no VoxVain SDK package to install yet. Call the HTTPS API directly: the examples above use only curl, Python with requests (pip install requests), and JavaScript with the built-in fetch (Node 18 or later, saved as a .mjs file and run with node). Each request returns audio bytes.

Pythonrequests
JavaScriptfetch
HTTPToday

Errors and limits

Errors return JSON: { "error": { "code": "invalid_request", "message": "…" } } with a 4xx or 5xx status. A 429 response includes Retry-After. Speech is $0.012 per 1,000 characters. GET /v1/usage reports characters, audio seconds and the customer charge.