API reference

Text-to-speech

POST/v1/audio/speech3 per 100 characters

The response body is the MP3 itself (audio/mpeg) — pipe it straight to a file or an audio element. Input is capped at 5,000 characters per request.

Voices: aria (female), orion (male). Credits are charged per started block of 100 input characters — a 250-character line costs 9 credits.

Request body

Field	Type	Description
inputrequired	string	The text to speak.
voicerequired	string	`aria` or `orion`.
model	string	Only `eroq-voice-one` today.

Example

curl https://eroq.ai/v1/audio/speech \
  -H "Authorization: Bearer $EROQ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "eroq-voice-one",
  "input": "That noise is the reactor missing its coolant flush. Again.",
  "voice": "aria"
}' \
  --output speech.mp3

Response

audio/mpeg

(binary MP3 body — audio/mpeg)