> ## Documentation Index
> Fetch the complete documentation index at: https://api-docs.ollang.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Grok Voice Transcribe

> xAI Grok Voice Transcribe 2 — 38+ language speech-to-text with word-level timestamps, speaker diarization, 2–8 channel multichannel input, and keyterm prompting.

**Grok Voice Transcribe 2** is xAI's current speech-to-text model. It transcribes **38+ languages** and is notable for two features that matter in production media work: **multichannel input**, where each recorded channel is transcribed separately, and **keyterm prompting** for names and terminology.

> [!NOTE]
>
> **Available in Ollang Workflows** as `grok-voice-transcribe` — Closed Captions, Subtitle Translation, and AI Dubbing · **New**. See the [Speech-to-Text catalog](https://api-docs.ollang.com/providers/speech-to-text.md).

## Model and coverage

| | |
| - | - |
| **Model** | Grok Voice Transcribe 2 (`grok-voice-transcribe-2.0`) |
| **Languages** | 38+, including regional variants such as `es-ES`, `pt-PT`, `ar-AE`, and `ar-SA` |
| **Text formatting** | Available in a subset of 11 languages |
| **Multichannel** | 2–8 channels, transcribed per channel |
| **Keyterms** | Up to 100 terms, 50 characters each |
| **Inputs** | WAV, MP3, OGG, Opus, FLAC, AAC, MP4, M4A, MKV, WebM, AVI, MOV, and raw PCM |

xAI retired Grok Voice Transcribe 1.0 in October 2026; requests to it are now served by 2.0.

## Key capabilities

* **Multichannel transcription.** When each speaker was recorded on their own channel, each channel is transcribed on its own, which avoids the attribution errors that come from separating mixed speech.
* **Speaker diarization** with a speaker label on every word.
* **Word-level timestamps**, which give subtitle segmentation precise boundaries.
* **Keyterm prompting** to enforce brand, product, and people names.

## Where it fits in a workflow

Grok Voice Transcribe 2 suits podcasts, interviews, and panel recordings with a channel per speaker, and content dense with names that a general model would misspell. For languages outside its list, use [AssemblyAI](https://api-docs.ollang.com/apis/stt-apis/assemblyai.md) or [ElevenLabs Scribe v2](https://api-docs.ollang.com/apis/stt-apis/elevenlabs-scribe.md); for genuinely difficult mixed audio, use [Agentic STT](https://api-docs.ollang.com/apis/stt-apis/ollang-agentic-stt.md).

## Trade-offs

* **38+ languages** is narrower than AssemblyAI (99), ElevenLabs Scribe v2 (90+), or Speechmatics (70+). Confirm your source language first.
* **Formatting coverage is partial**: automatic text formatting applies to 11 of its languages.
* **Newer model line**, with less production history than the established providers.

## Reference

* [Speech-to-Text provider catalog](https://api-docs.ollang.com/providers/speech-to-text.md)
* [xAI speech-to-text documentation](https://docs.x.ai/developers/model-capabilities/audio/speech-to-text)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.