Transcribe audio
zai/glm-asr-2512Turn a short recording into text.
- second
- Price: $0.00004
- Z.ai
- 5 min
Overview
Takes a short audio recording and returns what was said as text. The audio is sent as base64 and the gateway builds the upload for you, so no multipart handling is needed on the caller's side. Recordings must be brief and modest in size; longer material should be split and submitted in pieces. Billing counts the seconds of audio, measured from the recording itself when it carries a readable header and from the duration you declare otherwise.
The transcript, with the request id and the model that produced it.
Input
These go in the input object of the run request.
| Field | Type | Required | Description |
|---|---|---|---|
| audio_base64 | base64 | Yes | The recording, base64-encoded. |
| filename | string | No | A name for the uploaded file, which sets its extension. |
| content_type | string | No | Media type of the recording. |
| duration_seconds | number | No | Length of the recording, used for billing when the audio carries no readable header. |
| language | string | No | A language hint, forwarded with the upload. |
Requests up to 35 MB, audio up to 25 MB.
Example
Use your own API key and a saved idempotency key for each new job. Replace image or media placeholders with your own publicly reachable HTTPS URLs. Keep the same key and request body when recovering a timeout.
# Set once per job; reuse this key and the identical body after a timeout.
: "${AGENTSKY_IDEMPOTENCY_KEY:?Set a unique, saved key for this job}"
curl --fail-with-body https://gateway.agentsky.dev/v1/run \
-H "authorization: Bearer $AGENTSKY_API_KEY" \
-H "content-type: application/json" \
-H "Idempotency-Key: $AGENTSKY_IDEMPOTENCY_KEY" \
-d '{"provider":"zai","endpoint":"glm-asr-2512","input":{"audio_base64":"UklGRiQAAABXQVZFZm10IBAAAAABAAEA...","filename":"meeting.wav","content_type":"audio/wav"}}'
# If status is READY/RUNNING, poll GET /v1/runs/{runId} with the same API key.Pricing
$0.00004 per second using your plan when signed in. Read the final customer charge from price.amount.value after the run finishes. A RUNNING response is not the final bill.