Model Metadata
- type
- transcription
- name
- Grok Voice Transcribe 2.0
- description
- Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming
- family
- grok
- open weights
- No
- release date
- 2026-09-17
- modalities
- input: audio/wav, audio/mpeg, audio/ogg, audio/flac, audio/aac, audio/mp4; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: No; top_p: No; top_k: No
- limit
- context: 0; output: 0
Provider Variants 3
cloudflare-ai-gateway xai/grok-stt
Context Not recorded · Output Not recorded
- type
- transcription
- name
- Grok STT
- description
- Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming
- family
- grok
- open weights
- No
- release date
- 2026-09-17
- modalities
- input: audio/flac, audio/mpeg, audio/mp4, audio/x-matroska, audio/ogg, audio/wav, audio/aac, audio/pcm, audio/basic, audio/alaw; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: No; top_p: No; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 0; output: 0
- id
- xai/grok-stt
- canonical id
- xai/grok-voice-transcribe-2.0
- last updated
- 2026-09-17
- api
- workers-ai-run: base_url: https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai; sdk: aisdk: ai-gateway-provider
OpenRouter x-ai/grok-stt-1.0
Context Not recorded · Output Not recorded
- type
- transcription
- name
- Grok STT 1.0
- description
- Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming
- family
- grok
- open weights
- No
- release date
- 2026-09-17
- modalities
- input: audio/wav, audio/mpeg, audio/ogg, audio/flac, audio/aac, audio/mp4; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: No; top_p: No; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 0; output: 0
- id
- x-ai/grok-stt-1.0
- canonical id
- xai/grok-voice-transcribe-2.0
- last updated
- 2026-09-17
- api
- transcriptions: base_url: https://openrouter.ai/api/v1; sdk: aisdk: @ai-sdk/openai; opencodeai: @opencode/ai/protocols/openai-transcription
SpaceXAI grok-voice-transcribe-2.0
Context Not recorded · Output Not recorded
- type
- transcription
- name
- Grok Voice Transcribe 2.0
- description
- Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming
- family
- grok
- open weights
- No
- release date
- 2026-09-17
- modalities
- input: audio/wav, audio/mpeg, audio/ogg, audio/flac, audio/aac, audio/mp4; output: text
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: No; top_p: No; top_k: No; system_updates: No; effort_updates: No
- limit
- context: 0; output: 0
- id
- grok-voice-transcribe-2.0
- canonical id
- xai/grok-voice-transcribe-2.0
- last updated
- 2026-09-17
- api
- transcriptions: base_url: https://api.x.ai/v1; sdk: aisdk: @ai-sdk/xai