whatmodel.sh / stt / Grok Voice Transcribe 2.0
Grok Voice Transcribe 2.0
↗ share
+ contribute
Grok Voice Transcribe 2.0 is a closed-weights speech-to-text model from xAI, released September 2026. Licence: proprietary.
Score within the Open ASR English short-form WER (March 2026) comparison set only.
$ how it compares
The speech-to-text models ranked either side of Grok Voice Transcribe 2.0, out of 176 with a score, then more from xAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 1 |  Muse Voice Transcribe 1.0 | 71±3 | api $0.0030/audio min | ||
| 2 | Grok Voice Transcribe 2.0 | 70±3 | api $0.0017/audio min | ||
| 3 |  Saarika v2.5 | 70±5 | comparison only | ||
| 4 |  Universal-3.6 Pro Realtime | 70±3 | api $0.0075/audio min | ||
| 5 |  Linden 1 (Agent STT) | 69±3 | api $0.0050/audio min | ||
| more from xAI | |||||
| 38 | Grok Voice Transcribe 1.0 | 60±5 | comparison only | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
other tests2 not in a task · 96% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Pipecat STT Benchmark · pooled semantic WER (1000 smart-turn samples, Sonnet 5.5 judge) | 0.8% ✎ | ▃·▃▅·▅▅·▃▅██ beats 15/16 | 96% |
| raven.eval · German read/parliament 4-set WER mean (100 utt. each) | 8.2% ✎ | █··········█ beats 1/1 | — |
$ where to run it
Through an API
api · $0.0017/audio min · docs.x.ai ↗ · price sourceUSD per input audio minute: xAI Voice Pricing lists Speech to Text at $0.10 / hr (REST) (÷60); $0.20/hr streaming. xAI STT docs name grok-voice-transcribe-2.0 as the default model. Product: xAI Speech to Text API. API model: grok-voice-transcribe-2.0. Settings: REST (file). Price basis: published list rate, per-hour to per-minute scaling only. Exclusions: streaming. Currency: USD. xAI official models/pricing docs, observed 2026-09-25.
$ how the score was worked out · Pipecat STT Benchmark · seman… 96%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Pipecat STT Benchmark · semantic WER results table (pipecat-ai/stt-benchmark README) | 1 | 96% |
| prior · pull toward the middle | 4% | |
| weighted average | = 70.3 |
not counted (1)
| raven.eval · German ASR WER (public datasets) | raven.eval · German read/parliament 4-set WER mean (100 utt. each) [correct] | 8.2% | fewer than three models have this test yet, or this source ran it for this model alone |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json