GET

/v1/schemas/zai/audio/paas%2Fv4%2Faudio%2Ftranscriptions

kind inputactivity audiohash b9f7b164…extracted Oct 5, 2026version currentsource upstream spec ↗

Request body

8 properties · 2 required · 0 $defs
propertytypedescriptionconstraints
file*stringThe audio file to be transcribed. Supported audio file formats: `.wav / .mp3`. Specifications: file size ≤ `25 MB`, audio duration ≤ `30 seconds`.format: binary
model*enumThe model ID to invoke.glm-asr-2512 · default: "glm-asr-2512"
file_base64stringBase64 encoded audio file. Only one of file_base64 or file needs to be provided (if both are provided, file takes precedence).
promptstringIn long text scenarios, you can provide previous transcription results as context. Recommended to be less than 8000 characters.
hotwordsstring[]Hotword list to improve recognition accuracy for domain-specific vocabulary. Format example: ["person_name","place_name"]. Recommended not to exceed 100 items.items ≤ 100
streambooleanThis 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_idstringPassed 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_idstringUnique ID for the end user, 6–128 characters. Avoid using sensitive information.length ≥ 6 · length ≤ 128

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"zai","endpointId":"paas/v4/audio/transcriptions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}