Skip to content

Caedral technology

Available

Caedral Voice

English text-to-speech on Caedral infrastructure. Four voices, WAV output, billed from the Caedral Models pool. Notre does not run on this path.

caedral-voice-1 · $0.30 / 1M input tokens · max 2000 characters

Get API keyVoice docs

What

POST /v1/audio/speech accepts English (Latin script) text and returns WAV audio. Voices: caedral-f1, caedral-f2, caedral-m1, caedral-m2.

Limits

English (Latin script) only, max 2000 characters, WAV output. Native Voice bills the Caedral Models pool. Notre does not run on this path. The catalog id caedral-voice is a branded route to third-party gpt-audio and bills External Models — native Voice is caedral-voice-1 only.

Use

Same API key as the rest of Caedral. Input is limited to 2000 characters. Output is WAV. Use it for IVR prompts, accessibility, and product voiceovers that stay inside your Caedral Models pool.

  • Does not go through Notre
  • Does not claim multilingual coverage beyond English
  • Samples, when enabled, live on the catalog voice page

POST /v1/audio/speech

curl https://api.caedral.com/v1/audio/speech \
  -H "Authorization: Bearer $CAEDRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "caedral-voice-1",
    "input": "Your invoice is ready.",
    "voice": "caedral-f1"
  }'

Next