You're looking at a specific version of this model. Jump to the model overview.
xai /grok-speech-to-text:cfeb8cf4
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| audio |
string
|
Audio file to transcribe. Supports WAV, MP3, WebM, OGG, M4A, FLAC, AAC, MP4, Opus. Max 500MB.
|
|
| language |
None
|
auto
|
Language code for the audio (e.g. 'en', 'fr', 'de'). Used to enable inverse text normalization when 'format_text' is true. Set to 'auto' to let the model auto-detect the language.
|
| format_text |
boolean
|
False
|
Enable inverse text normalization, which converts spoken-form numbers, currencies, and units to their written form (e.g. 'one hundred dollars' becomes '$100'). Requires 'language' to be set.
|
| multichannel |
boolean
|
False
|
Transcribe each audio channel independently. The output will include a per-word 'channel' index.
|
| diarize |
boolean
|
False
|
Enable speaker diarization. Each word in the output will include a 'speaker' index identifying who spoke it.
|
| timestamps |
boolean
|
False
|
Include word-level start and end timestamps in the output.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'properties': {'duration': {'title': 'Duration', 'type': 'number'},
'language': {'nullable': True,
'title': 'Language',
'type': 'string'},
'text': {'title': 'Text', 'type': 'string'},
'words': {'items': {'properties': {'channel': {'nullable': True,
'title': 'Channel',
'type': 'integer'},
'end': {'title': 'End',
'type': 'number'},
'speaker': {'nullable': True,
'title': 'Speaker',
'type': 'integer'},
'start': {'title': 'Start',
'type': 'number'},
'text': {'title': 'Text',
'type': 'string'}},
'required': ['text', 'start', 'end'],
'type': 'object'},
'nullable': True,
'title': 'Words',
'type': 'array'}},
'required': ['text', 'duration'],
'title': 'Output',
'type': 'object'}