GET

/v1/schemas/groq/audio/openai%2Fv1%2Faudio%2Fspeech

kind inputactivity audiohash cead60c8…extracted Aug 15, 2026version currentsource upstream spec ↗

Request body

6 properties · 3 required · 0 $defs
propertytypedescriptionconstraints
model*string | enumOne of the [available TTS models](/docs/text-to-speech).
input*stringThe text to generate audio for.
voice*stringThe voice to use when generating the audio. List of voices can be found [here](/docs/text-to-speech).
response_formatenumThe format of the generated audio. Supported formats are `flac, mp3, mulaw, ogg, wav`.flac | mp3 | mulaw | ogg | wav · default: "mp3"
sample_rateenumThe sample rate for generated audio8000 | 16000 | 22050 | 24000 | 32000 | 44100 · +1 more · default: 48000
speednumberThe speed of the generated audio.0.5 ≤ n ≤ 5 · default: 1

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"groq","endpointId":"openai/v1/audio/speech","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}