Grok Voice Transcribe 2.0
Grok Voice Transcribe 2.0 is SpaceXAI's current speech-to-text model. Use the explicit model ID grok-voice-transcribe-2.0 for REST file transcription or WebSocket streaming; the live docs price them at $0.10 and $0.20 per audio hour.
The release adds low-cost transcription with timestamps, speaker and channel separation, domain keyterms and live turn detection. The current reference and release notes agree that 2.0 is the default; explicit selection still makes an integration’s intended version clear.
Checked October 7 against SpaceXAI’s speech-to-text reference and release notes. The October 2 notes state that 1.0 reached end of life and requests to its slug route to 2.0 at the same price. Provider accuracy comparisons are not independent benchmarks.
- Transcribe interviews and meetings.
- Separate call-center channels or speakers.
- Generate live captions and dictation.
- Bias recognition toward product and domain terms.
- Detect turn completion in streaming voice workflows.
The REST /v1/stt endpoint accepts a file or server-downloadable URL and supports files up to 500 MB. The WebSocket endpoint streams raw audio and can return interim and final transcripts. REST is $0.10 per hour and streaming is $0.20 per hour.
The response can include word-level timestamps and detected language. Streaming and supported REST options add diarization, up to eight interleaved channels, keyterm biasing, filler-word control, voice-activity thresholds, endpointing, and Smart Turn.
The current docs name grok-voice-transcribe-2.0 as the default. On October 2, 2026, grok-voice-transcribe-1.0 reached end of life: old-slug requests route to 2.0 at the same price. This compatibility redirect does not keep the old backend independently available. Use the explicit 2.0 ID and check SDK and third-party behavior separately.
Grok Voice Transcribe 2.0 FAQ
Common questions about Grok Voice Transcribe 2.0.
What model ID should I use for Grok Voice Transcribe 2.0?+
Pass grok-voice-transcribe-2.0 explicitly. Current first-party pages agree that it is the default; 1.0 reached end of life on October 2 and old-slug requests route to 2.0.
How much does Grok speech to text cost?+
SpaceXAI lists REST transcription at $0.10 per audio hour and streaming transcription at $0.20 per audio hour.
Does it support speaker diarization and multichannel audio?+
Yes. The current guide documents speaker IDs plus separate transcripts for up to eight interleaved channels, with an Opus limitation for multichannel streaming.