{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/grok-voice-think-fast-2-0/","md":"https://postcutoff.com/m/grok-voice-think-fast-2-0/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"grok-voice-think-fast-2-0","name":"Grok Voice Think Fast 2.0","org":"xAI","family":"Grok Voice","released":"2026-07-29","status":"legacy","type":"audio/speech","modality_in":["audio","text"],"modality_out":["audio","text"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"per_minute":0.08,"unit":"USD per minute of audio ($4.80/hr), plus $0.004 per text input (as listed on the xAI pricing page)","source":"https://docs.x.ai/developers/pricing"},"price_line":"$0.08 per minute","access":[{"provider":"xAI API (Voice Agent / speech-to-speech, WebSocket)","model_id":"grok-voice-think-fast-2.0","endpoint":"wss://api.x.ai/v1/realtime?model=grok-voice-think-fast-2.0","docs":"https://docs.x.ai/developers/model-capabilities/audio/voice-agent"},{"provider":"xAI API (alias)","model_id":"grok-voice-latest","docs":"https://docs.x.ai/developers/model-capabilities/audio/voice-agent"},{"provider":"Web app","url":"https://grok.com"}],"capabilities":[{"name":"Reasoning while speaking","detail":"Speech-to-speech model that reasons in real time (reasoning effort 'high' by default, can be set to 'none'); 97.2% Big Bench Audio, 82.9 on the Artificial Analysis Speech-to-Speech Quality Index (vs 75.7 for v1.0).","first":false,"discovered":"launch","source":"https://x.ai/news/grok-voice-think-fast-2"},{"name":"Faster first audio","detail":"Time to first audio cut from 1.25 s (v1.0) to 0.70 s; Full Duplex Bench 95.1%, tau-voice Bench 56.5% (xAI-reported).","first":false,"discovered":"launch","source":"https://x.ai/news/grok-voice-think-fast-2"},{"name":"Built-in server-side tools","detail":"Web search, X search, collections (file) search and remote MCP callable from inside a voice session, plus custom functions.","first":false,"discovered":"launch","source":"https://docs.x.ai/developers/model-capabilities/audio/voice-agent"},{"name":"OpenAI Realtime-compatible protocol","detail":"Largely compatible with the OpenAI Realtime SDK: change base URL to https://api.x.ai/v1 and the API key (minor event-name differences).","first":false,"discovered":"launch","source":"https://docs.x.ai/developers/model-capabilities/audio/voice-agent"}],"entry":"2026-07-29-grok-voice-think-fast-2","notes":"Superseded by Grok Voice 3.0 on 2026-10-14 (grok-voice-latest now points to 3.0; see entry 2026-10-14-grok-voice-3). Released 2026-07-29; grok-voice-latest switched to it on 2026-08-05. Predecessor grok-voice-think-fast-1.0 can still be pinned. 20+ languages; audio PCM (8-48 kHz), Opus 24 kHz, G.711 mu-law/A-law; server VAD, session resumption (30 min), custom cloned voices. xAI says Starlink A/B tests raised sales conversion and support containment. Benchmarks are xAI-reported.","verified":"2026-10-14","body_md":"xAI's realtime voice-agent model (also used in the Grok app, Tesla vehicles and Starlink support).\n\n```python\n# OpenAI Realtime-compatible WebSocket\nimport websockets, os\nurl = \"wss://api.x.ai/v1/realtime?model=grok-voice-think-fast-2.0\"\nws = await websockets.connect(url, additional_headers={\"Authorization\": f\"Bearer {os.environ['XAI_API_KEY']}\"})\n```\n\nSources: https://x.ai/news/grok-voice-think-fast-2 · https://docs.x.ai/developers/model-capabilities/audio/voice-agent · https://docs.x.ai/developers/pricing","page_url":"https://postcutoff.com/m/grok-voice-think-fast-2-0/","standing":{"kind":"speech and audio","newer_count":39,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"grok-tts","name":"Grok Text to Speech (Grok TTS API)","org":"xAI","released":"2026-04-17","page_url":"https://postcutoff.com/m/grok-tts/"},"after":{"id":"grok-voice-transcribe-2-0","name":"Grok Voice Transcribe 2.0","org":"xAI","released":"2026-09-18","page_url":"https://postcutoff.com/m/grok-voice-transcribe-2-0/"},"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}