Hume AI

API

Expressive text-to-speech and real-time speech-to-speech voice API

Price: Free tier, then paid
Access: API key

About

Hume AI offers Octave, a text-to-speech model that follows acting instructions, and EVI, a real-time speech-to-speech interface for voice agents. Voice design and cloning are included. The free plan has 10,000 characters and 5 EVI minutes a month.

What you can do with it

Generate expressive speech from text with acting instructions
Build a real-time voice agent that responds to the user's tone of voice
Design a new voice from a text prompt or clone one from a short sample

Get started

Sign in to the Hume Portal and copy your API key
Export it as HUME_API_KEY

Example

curl -X POST "https://api.hume.ai/v0/tts/file" \
  -H "X-Hume-Api-Key: $HUME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "utterances": [{"text": "Welcome back. How was your day?", "description": "A warm, calm narrator"}],
    "format": {"type": "mp3"}
  }' \
  --output speech.mp3

Details

Hosting: Hosted service
Available in: Worldwide
Official SDKs: JavaScript/TypeScript, Python, C#
MCP server: Local