Voice presets

Overview

Presets are the built-in speakers. Pass a preset id as voice, and the same speaker reads every request.

curl https://api.sprag.ai/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SPRAG_API_KEY" \
  -d '{
    "model": "chorus",
    "input": "The quarterly numbers are in and they look good.",
    "voice": "dominic",
    "response_format": "mp3"
  }' \
  --output out.mp3

List presets

GET /v1/audio/voices?model=chorus lists the presets. List the voices rather than hardcoding an id. The set can change.

curl "https://api.sprag.ai/v1/audio/voices?model=chorus" \
  -H "Authorization: Bearer $SPRAG_API_KEY"

Each entry carries the id to pass as voice, a name, and a description. For a playable sample of each voice, use the voice library in the app.

If voice names no voice in the listing, the request returns HTTP 400 with the error code unknown_voice.

Accent and language

Every preset reads any supported language. A voice's listed language names the accent the speaker carries, not a limit on what they read. A voice listed as German reads English, and sounds like a German speaker reading English.

To define a speaker in words rather than pick one, see Voice design.