← All models
Pipecat's Smart Turn model
smart-turn
Speech to Textby smart-turn
An open source, community-driven and native audio turn detection model by Pipecat AI.
Pricing
- Price
- 0.139 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| audio_urlrequired | string | The URL of the audio file to be processed. |
Output
| Field | Type | Description |
|---|---|---|
| metrics | object | The metrics of the inference. |
| prediction | integer | The predicted turn type. 1 for Complete, 0 for Incomplete. |
| probability | number | The probability of the predicted turn type. |