As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/grok-voice-transcribe-2-0/

# Grok Voice Transcribe 2.0

xAI, Grok Voice family. Status: current. Type: speech and audio. Released: 2026-09-18.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| xAI API (REST) | `grok-voice-transcribe-2.0` | https://api.x.ai/v1/stt | https://docs.x.ai/developers/model-capabilities/audio/speech-to-text |
| xAI API (WebSocket streaming) | `grok-voice-transcribe-2.0` | wss://api.x.ai/v1/stt | https://docs.x.ai/developers/model-capabilities/audio/speech-to-text |

## Pricing

- Per hour, batch: $0.10
- Per hour, streaming: $0.20
- Unit as published: USD per hour of audio (REST batch / WebSocket streaming); diarization, timestamps and key-term biasing included
- Source: https://x.ai/news/grok-voice-transcribe-2
- Last checked: 2026-09-29

## Specs

- Input: audio
- Output: text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 23. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from xAI: Grok Voice Think Fast 2.0 (2026-07-29) https://postcutoff.com/m/grok-voice-think-fast-2-0/
- After it from xAI: Grok Voice 3.0 (2026-10-14) https://postcutoff.com/m/grok-voice-3-0/
- Closed weights; access is hosted only.

## What stands out

- Top streaming STT accuracy (claimed): xAI says it ranks #1 for accuracy among 32 streaming models on the Artificial Analysis leaderboard; multilingual short-phrase WER 20.6% -> 6.8% vs v1.0 ('2x as accurate'). Source: https://x.ai/news/grok-voice-transcribe-2
- Very low price with diarization included: $0.10/hr batch and $0.20/hr streaming, with speaker diarization, word timestamps, up to 8-channel multichannel and 100 key terms per request at no extra cost. Source: https://x.ai/news/grok-voice-transcribe-2

## Notes

Launched 2026-09-18 as drop-in upgrade of the Grok STT API (first released 2026-04-17 with grok-voice-transcribe-1.0, which can be pinned but will be deprecated). Up to 500 MB files; WAV/MP3/OGG/Opus/FLAC/AAC/MP4/M4A/MKV plus raw PCM/mu-law/A-law at 8-48 kHz; Smart Turn end-of-turn detection, VAD, inverse text normalization, filler removal, mid-recording language switching. Docs list ~25 languages for formatting.

```bash
curl https://api.x.ai/v1/stt -H "Authorization: Bearer $XAI_API_KEY" \
  -F model=grok-voice-transcribe-2.0 -F file=@call.wav -F diarize=true
```

Sources: https://x.ai/news/grok-voice-transcribe-2 · https://docs.x.ai/developers/model-capabilities/audio/speech-to-text · https://x.ai/news/grok-stt-and-tts-apis

Model page: https://postcutoff.com/m/grok-voice-transcribe-2-0/