Repository Public
1<!-- source: https://docs.x.ai/developers/models/speech-to-text (from https://docs.x.ai/llms-full.txt, retrieved 2026-09-19T05:28:55Z) -->2#### Models34# Speech to Text56The Speech to Text API transcribes audio into text. Use `grok-voice-transcribe-1.0` or `grok-voice-transcribe-2.0`; the default is `grok-voice-transcribe-2.0`. Use the REST endpoint for file-based batch transcription, or the streaming endpoint for real-time low-latency transcription.78## At a glance910| | Details |11|---|---|12| **Modalities** | Audio → Text |13| **REST pricing** | / hr |14| **Streaming pricing** | / hr |15| **Region** | us-east-1 |1617## Pricing1819| | Details |20|---|---:|21| **REST (per hour)** | / hr |22| **Streaming (per hour)** | / hr |2324## Rate Limits2526| | REST | Streaming |27|---|---:|---:|28| **RPS** (Requests per second) | | |29| **Concurrent sessions** | — | per team |3031## Capabilities3233* REST and streaming transcription34* Multiple audio formats (WAV, MP3, WebM, OGG, M4A)35* Multiple languages36* Real-time interim results (streaming)37* Keyterm prompting for domain-specific vocabulary38* Smart Turn end-of-turn detection (streaming) — ML-based prediction of whether the speaker has finished their thought3940## Availability4142| | Details |43|---|---|44| **Cluster** | us-east-1 |4546## Documentation4748* [Speech to Text Guide](/developers/model-capabilities/audio/speech-to-text) — Getting started with speech to text49* [Voice Overview](/developers/model-capabilities/audio/voice) — Overview of all voice capabilities50* [Pricing](/developers/pricing#voice-api-pricing) — Full pricing overview51