Grok Voice Transcribe 2.0 released
xAI · Model release
Source confirmed
Data as of September 30, 2026 · How the score is built
CurrentProprietaryNon-Reasoning
Released Sep 18, 2026N/A contextxAI model documentation
Grok Voice Transcribe 2.0
Decision readingGrok Voice Transcribe 2.0 is tracked, but not publicly ranked yet. Published speech or voice results from Grok Voice Transcribe 2.0 launch evaluation appear below. They do not produce a weighted text-model score.
Released Sep 18, 2026 — see all recent releases
Grok Voice Transcribe 2.0 will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Voice benchmark evidence
Grok Voice Transcribe 2.0 launch evaluation is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Short-phrase multilingual WER
6.8%
Short-phrase WER, Grok Voice Transcribe 1.0
20.6%
Independent streaming-accuracy leaderboard rank
#1 of 32
Overall accuracy vs 1.0
2x
Batch price
$0.10 per hour
Streaming price
$0.20 per hour
Provider API ID
grok-voice-transcribe-2.0
Provider launch snapshot · xAI · 2026-09-18 · lower WER is better; the per-category charts publish no readable figures
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Radar
Full release historyGrok Voice Transcribe 2.0 release history
Radar confirmed these at the source. Use Grok Voice Transcribe 2.0 in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- grok-voice-transcribe-2.0xAI model documentation
- Context window
- N/A
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Released September 18, 2026 in the xAI Speech-to-Text API for batch and streaming transcription, with word-level timestamps and confidence scores, speaker diarization at no extra cost, multichannel transcription of up to 8 channels, key term biasing of up to 100 terms per request, text formatting, filler-word removal, and smart turn detection. Existing integrations pick up the accuracy change with no code edits. xAI says it will soon be the API default and that Grok Voice Transcribe 1.0 will be deprecated in the coming weeks; callers can pin grok-voice-transcribe-1.0 during the transition. BenchLM does not track the 1.0 model.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordxAI model documentation
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Grok Voice Transcribe 2.0, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Grok Voice Transcribe 2.0 is a proprietary model with a N/A context window. No explicit reasoning mode is documented in this profile.
Released September 18, 2026 in the xAI Speech-to-Text API for batch and streaming transcription, with word-level timestamps and confidence scores, speaker diarization at no extra cost, multichannel transcription of up to 8 channels, key term biasing of up to 100 terms per request, text formatting, filler-word removal, and smart turn detection. Existing integrations pick up the accuracy change with no code edits. xAI says it will soon be the API default and that Grok Voice Transcribe 1.0 will be deprecated in the coming weeks; callers can pin grok-voice-transcribe-1.0 during the transition. BenchLM does not track the 1.0 model.
Grok Voice Transcribe 2.0 is a display-only speech-to-text model built on the audio foundation model behind Grok Voice. Transcription results remain separate from BenchLM’s weighted text-model ranking.
Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated September 30, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Grok Voice Transcribe 2.0 perform overall in AI benchmarks?
Grok Voice Transcribe 2.0 has published speech or voice results in Grok Voice Transcribe 2.0 launch evaluation. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Does Grok Voice Transcribe 2.0 have full benchmark coverage on BenchLM?
No. Grok Voice Transcribe 2.0's speech or voice results appear in Grok Voice Transcribe 2.0 launch evaluation, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of Grok Voice Transcribe 2.0?
Grok Voice Transcribe 2.0 has a reported context window of N/A in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.