Attributes
- Provider: openai
- Category: Speech to Text
Parameters
| Name | Description | Type | Required | Enums |
|---|---|---|---|---|
| prompt | Optional text to guide the model’s style or continue a previous segment. | string | No | - |
| url | Public http(s) URL of the audio file (max 25 MB). | string | Yes | - |
| language | ISO-639-1 language hint for transcription. | string | No | - |
| response_format | Output format. verbose_json recommended for duration and timestamps. | string | No | json, text, srt, verbose_json, vtt |
| temperature | Sampling temperature; higher values increase randomness. | number | No | - |
| timestamp_granularities | Timestamp detail levels. Requires response_format=verbose_json when non-empty. | string[] | No | word, segment |
Pricing
Unit: $/sec
| Pricing |
|---|
| $0.0001/sec |
