Deepgram

API

Speech-to-text, text-to-speech and voice agent APIs

Price
Free credits, then paid
Access
API key

About

Deepgram provides speech-to-text, text-to-speech and voice agent APIs for recorded files and live audio streams. It suits apps that transcribe calls or meetings or run voice bots. It can also be self-hosted, and new accounts get $200 in free credit.

What you can do with it

  • Transcribe recorded audio files or live audio streams
  • Generate spoken audio from text with Aura voices
  • Run voice agents that listen, think and speak in one pipeline

Get started

  1. Sign up in the Deepgram Console ($200 free credit)
  2. Create an API key

Example

curl -X POST "https://api.deepgram.com/v1/listen?model=nova-3&smart_format=true" \
  -H "Authorization: Token $DEEPGRAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://dpgr.am/spacewalk.wav"}'

Details

Hosting
Hosted service, Self-hosted
Available in
Worldwide
Official SDKs
JavaScript/TypeScript, C#, Python, Go, Rust, Java
MCP server
Local

Tasks

Alternatives

Other tools for the same tasks.

Last checked on .