GET
/v1/schemas/zai/audio/paas%2Fv4%2Faudio%2Ftranscriptions
Accept:
Request body
8 properties · 2 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| file* | string | The audio file to be transcribed. Supported audio file formats: `.wav / .mp3`. Specifications: file size ≤ `25 MB`, audio duration ≤ `30 seconds`. | format: binary |
| model* | enum | The model ID to invoke. | glm-asr-2512 · default: "glm-asr-2512" |
| file_base64 | string | Base64 encoded audio file. Only one of file_base64 or file needs to be provided (if both are provided, file takes precedence). | |
| prompt | string | In long text scenarios, you can provide previous transcription results as context. Recommended to be less than 8000 characters. | |
| hotwords | string[] | Hotword list to improve recognition accuracy for domain-specific vocabulary. Format example: ["person_name","place_name"]. Recommended not to exceed 100 items. | items ≤ 100 |
| stream | boolean | This parameter should be set to `false` or omitted when using synchronous calls. It indicates that the model returns all content at once after generating all content. Default is `false`. If set to `true`, the model will return generated content in chunks via s… | default: false |
| request_id | string | Passed by the user side, needs to be unique; used to distinguish each request, 6–64 characters. If not provided by the user side, the platform will generate one by default. | length ≥ 6 · length ≤ 64 |
| user_id | string | Unique ID for the end user, 6–128 characters. Avoid using sensitive information. | length ≥ 6 · length ≤ 128 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"zai","endpointId":"paas/v4/audio/transcriptions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}