VoxNeura API

The VoxNeura REST API lets you integrate AI text-to-speech directly into your applications. Generate lifelike speech with a single voice or multi-speaker conversations, manage voices, and track usage — all with a simple HTTP API.

All API requests must include your API key in the X-API-Key header. You can create and manage your API keys from Settings → Developer.

curl https://api.voxneura.com/api/v1/tts/generate \
  -H "X-API-Key: vn_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{ "text": "Hello", "voice_id": "..." }'

Both generation endpoints accept an optional parameters object to fine-tune the output. All fields are optional — defaults are applied when omitted.

Connect VoxNeura to Claude and drive it from a conversation: generate speech, images, video clips — or a complete one-prompt film. No install and no API key — you sign in with your VoxNeura account and it uses the same VoxCredits as the app.

In Claude, open Settings → Connectors → Add custom connector, paste the URL below, click Connect, then sign in and approve access:

https://mcp.voxneura.com/mcp

A VoxNeura window opens for you to log in and grant access — you can revoke it anytime in Settings → Developer.

Tools: generate_speech, generate_image, generate_video, get_film_quote, create_film, get_job_status, list_voices, get_credits, list_capabilities. Try: "Use VoxNeura to make a 1-minute film about a fisherman and the sea goddess."

All error responses return JSON with error: true and a message field describing the issue.

{
  "error": true,
  "message": "insufficient characters — upgrade your plan or purchase more"
}