Grok Voice STT 1.0 is xAI's speech-to-text model. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.
- Released
- 2mo ago
- Pricing
- Not published
Sources:models.dev
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- xAI
- Model family
- Grok Voice
- Type
- Audio model
- Predecessor
- —
- Successor
- —
- Released
- August 4, 2026
- Model ID
xai/grok-voice-stt-1.0- Openness
- Closed
- License
- —
- Input modalities
- audio
- Output modalities
- text
- Modality
- audio->text
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- xai/grok-voice-stt-1.0
- Last updated
- 2026-08-04
- Model context
- 15K
- Model output limit
- 15K
- Open weights
- No
- File attachments
- Yes
- Reasoning
- No
- Tool calling
- No
- Temperature control
- No
Complete source record (JSON)
{
"id": "xai/grok-voice-stt-1.0",
"name": "Grok Voice STT 1.0",
"description": "Grok Voice STT 1.0 is xAI's speech-to-text model. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.",
"last_updated": "2026-08-04",
"attachment": true,
"reasoning": false,
"tool_call": false,
"temperature": false,
"modalities": {
"input": [
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 15000,
"output": 15000
},
"release_date": "2026-08-04",
"open_weights": false
}Infrastructure
Provider availability
Provider-specific media pricing is not available in the imported source data yet.