Transcribe with timestamps
fish_audio/transcribe-1Turn a recording into text with per-segment timings.
- second
- $0.0002
- Fish Audio
- 5 min
Overview
Takes an audio recording and returns what was said, the length of the audio, and a breakdown into segments. The language is detected automatically and reported back; a hint may be supplied but does not override the detection. Segment timings marking where each piece of text starts and ends can be requested, which is what makes subtitle generation and jumping to a position in the source possible, at the cost of some latency on short clips. Billing counts the seconds of audio the transcriber reports.
The transcript, the duration in seconds, the detected language, and the segments with their start and end times.
Input
These go in the input object of the run request.
| Field | Type | Required | Description |
|---|---|---|---|
| audio_base64 | base64 | Yes | The recording, base64-encoded. |
| language | string | No | A language hint; detection still runs and is reported back. |
| ignore_timestamps | boolean | No | Set false to get per-segment start and end times. |
Requests up to 35 MB, audio up to 25 MB.
Example
A call that works, with your own key.
curl https://gateway.agentsky.dev/v1/run \
-H "authorization: Bearer $AGENTSKY_API_KEY" \
-H "content-type: application/json" \
-d '{"provider":"fish_audio","endpoint":"transcribe-1","input":{"audio_base64":"UklGRiQAAABXQVZFZm10IBAAAAABAAEA...","ignore_timestamps":false}}'Pricing
$0.0002 per second on the default plan. Every run carries its price in the response.