GET
/v1/schemas/cartesia/audio/infill%2Fbytes
Accept:
Request body
10 properties · 0 required · 3 $defs| property | type | description | constraints |
|---|---|---|---|
| left_audio | string | Audio clip that comes before the infill transcript: `left_audio` -> `transcript` -> `right_audio` | format: binary |
| right_audio | string | Audio clip that comes after the infill transcript: `left_audio` -> `transcript` -> `right_audio` | format: binary |
| model_id | enum | The ID of the model to use for generating audio | sonic-3 | sonic-3-2026-01-12 |
| language | enum | The language of the transcript | en | fr | de | es | pt | zh · +38 more |
| transcript | string | The infill text to generate. For best results, use longer transcripts to give the model more flexibility to adapt to the rest of the audio. | |
| voice_id | string | The ID of the voice to use for generating audio | |
| output_format[container] | enum | The format of the output audio | raw | wav | mp3 |
| output_format[sample_rate] | enum | The sample rate of the output audio | 8000 | 16000 | 22050 | 24000 | 44100 | 48000 |
| output_format[encoding] | enum | Required for `raw` and `wav` containers. | pcm_f32le | pcm_s16le | pcm_mulaw | pcm_alaw |
| output_format[bit_rate] | integer | Required for `mp3` containers. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"cartesia","endpointId":"infill/bytes","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}