Docs
Get an API key

List Audio Models

GET /v1/audio/models Deprecated View .md

The speech and transcription models the API serves, with their price per second. Deprecated: GET /v1/models?output_modalities=speech (or transcription) lists the same models with everything they accept.

OK

application/json · audio-models-response-payload

2 fields
  • speech array of objects required

    Text-to-speech models, for POST /v1/audio/speech.

    4 fields
    • id string required

      The model id to send as model.

    • created integer required

      When the model was added, in Unix seconds.

    • price_per_second number required

      US dollars per second of audio (produced for speech, read for transcription).

    • price number required deprecated

      The same value as price_per_second, kept for clients that read it.

  • transcription array of objects required

    Transcription models, for POST /v1/audio/transcriptions.

    4 fields
    • id string required

      The model id to send as model.

    • created integer required

      When the model was added, in Unix seconds.

    • price_per_second number required

      US dollars per second of audio (produced for speech, read for transcription).

    • price number required deprecated

      The same value as price_per_second, kept for clients that read it.

curl https://api.vultrinference.com/v1/audio/models \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY"
Response · 200
{
    "speech": [
        {
            "id": "qwen3-tts-12hz-1.7b",
            "created": 0,
            "price_per_second": 0.0,
            "price": 0.0
        }
    ],
    "transcription": [
        {
            "id": "qwen3-tts-12hz-1.7b",
            "created": 0,
            "price_per_second": 0.0,
            "price": 0.0
        }
    ]
}