Grok Voice Transcribe 2.0
Grok Voice Transcribe 2.0 is worth evaluating for general LLM work when its provider route and context window match the workload.
Use it for
- Teams evaluating general LLM work
- Buyers comparing 1 tracked provider route
Do not use it for
- Vision or document-understanding workloads
- Strict JSON or tool-calling flows
- Family
- Grok Voice
- Released
- 2026-09-18
- Specialization
- speech-recognition
- Openness
- Proprietary
- License
- ProprietaryCommercial use: conditional
- Weights
- Not released
- Code
- Unknown
Cheapest of 1 route · xAI Console
About
Grok Voice Transcribe 2.0 (API id grok-voice-transcribe-2.0) is xAI's latest speech-to-text / ASR model, announced September 18, 2026 on x.ai/news. Specialized transcription API, not a chat LLM. First-party: twice as accurate as Grok Voice Transcribe 1.0 at the same price; ranks first for accuracy among 32 streaming models on the public Artificial Analysis leaderboard (first-party ranking claim); multilingual (dozens of languages, auto language detect, mid-recording language switch); batch and streaming STT; word-level timestamps with confidence; speaker diarization at no extra cost; multichannel up to 8 channels; key-term biasing (up to 100 terms); text formatting for numbers/dates/currencies/phones/emails.
Top use-case fit
No primary decision-task fit is mapped for this model yet.
Provider price ladder
Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| xAI Console | - | - | ServerlessPartial |
Available via routers & gateways(1)
Capabilities
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
Grok Voice Transcribe 2.0grok-voice-transcribe-2.0Grok Voice Transcribe 2Cheapest of 1 route · xAI Console