Capabilities
Explore what Grok Speech-to-Text supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- xAI
- Product
- Speech-to-Text
- Release Date
- Apr 2026
- Data Policy
- No training
- Region
- Global
- Input
- Audio
- Output
- Text
Playground
Try Grok Speech-to-Text by xAI. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Grok Speech-to-Text.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| xAI | Not specified | Text | $0.0014 / minute | — | xai/stt:xai |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 500000000 |
| Max seconds | 3600 |
| Formats | wav, mp3, ogg, opus, flac, aac, mp4, m4a |
Provider Notes
xAI's /v1/stt service exposes one logical model and does not accept an upstream model identifier. The same AudioLab slug supports uploaded audio and live WebSocket transcription. Text formatting requires an explicit language; multichannel channel counts require multichannel=true; both paths accept up to 100 keyterms of at most 50 characters each.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-F 'model=xai/stt' \
-F 'file=@recording.wav'Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | xai/stt — Required model identifier. |
channels / multichannel (batch) | View Accepted Values |
filler_words / format (batch) | View Accepted Values |
endpointing / filler_words (realtime) | View Accepted Values |
smart_turn / smart_turn_timeout (realtime) | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max bytes | 500000000 |
| Max seconds | 3600 |
| Formats | wav, mp3, ogg, opus, flac, aac, mp4, m4a |
Similar Models
Explore more speech-to-text and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| MAI-Transcribe 2Microsoft Azure | Not specified | $0.0014 / minute | — |
| Gemini 3.5 TranscribeGoogle Gemini | Not specified | $0.0043 / minute | — |
| Saaras v4Sarvam AI | Not specified | ₹0.425 / minute | — |
| saaras-v4-batchSarvam AI | Not specified | ₹0.425 / minute | — |
| qwen-audio-3.0-asr-flashAlibaba Cloud Model Studio | Not specified | $0.0018 / minute | — |
| qwen-audio-3.0-asr-flash-filetransAlibaba Cloud Model Studio | Not specified | $0.0018 / minute | — |
