[ Deepgram ]

Deepgram Aura

Deepgram Aura from Deepgram: a text-to-speech model. Every model below its source price, and the cheapest provider wins every request. Priced in USD per 1M UTF-8 bytes, paid in USDF, with no subscription and no minimum.

DeepgramauraServingspeechMax input: 2,000 characters

Max input

2,000

characters

Prices show once you sign in. Sign in

Models with a zero-retention route use it by default. A model marked 'provider may keep data' is served by a provider that may keep request data; choosing it is your choice.

Model ID
aura
Modality
speech
Unit
USD per 1M UTF-8 bytes
Endpoints
/v1/audio/speech

Make your first request

Responses include a receipt with the exact cost. Need a key? Create one.

Without an account, send the same request to /x402/v1/audio/speech with no credentials and the gateway answers 402 with a quote. Pay per request.

curl https://api.usdf.fi/v1/audio/speech \
  -H "Authorization: Bearer $USDF_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "aura", "input": "Hello", "response_format": "mp3"}' \
  --output speech.mp3  # the response body is audio bytes

Confirm it's you

Confirm to continue the action you started.

Checking confirmation options…