On 2026-11-06, Cursor's changelog shipped Voice Chat with Agents: realtime two-way voice calls with coding agents in the Agents Window, IDE, web, and iOS. Dictation remains a separate feature. Grok Voice handles listening and speaking (voices include Ara, Eve, Leo, Rex, Sal); the coding agent still uses the model you picked. With Privacy Mode on, voice chat runs with zero data retention. A signed-in Cursor account is required (API-key-only sessions cannot start a call).

Key Takeaways

  • ✓Source: Cursor changelog Voice Chat with Agents (2026-11-06) + docs at cursor.com/docs/agent/voice-chat
  • ✓UX: start when the agent is idle and the chat input is empty via the waveform button; during a call hand off coding, read-only check diffs/runs/history, switch Project workers
  • ✓Split: Grok Voice listens and speaks; the coding agent keeps your chosen model and speaks short progress/done notes
  • ✓Privacy/limits: Privacy Mode = zero data retention for voice; signed-in account required; API-key-only sessions cannot call; ~10 min silence hangup by default plus a daily call limit
  • ✓Not dictation: Cmd+Shift+Space still toggles dictation (formerly Voice Mode); Voice Chat is two-way speech with no dedicated shortcut
Cursor Ships Voice Chat: Realtime Two-Way Calls with Agents on Agents Window, IDE, Web, and iOS via Grok Voice
🖼️Official Media
Click to view high-res
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Core Background & Industry Pain Points

Long-running coding agents still push most status checks through typing. On 2026-11-06, Cursor's changelog shipped Voice Chat with Agents: realtime two-way calls across the Agents Window, IDE, web, and iOS, explicitly separate from dictation (formerly Voice Mode).

Architecture Highlights & Internals

Grok Voice handles listening and speaking; the coding agent keeps your selected model. During a call you can hand off coding, run read-only lookups on diffs/runs/history, and switch Project workers. The coding agent speaks short progress/done notes; otherwise the call reads the written reply. With Privacy Mode on, voice runs with zero data retention and cloud transcript sync is off.

Authoritative Benchmarks & Measured Scores

No vendor ASR/TTS or coding-productivity leaderboard. Verifiable facts: Agents Window, IDE, web, iOS; iOS supports "Hey Siri, call Cursor" and Lock Screen Live Activity mute/hang-up; default hang-up after ~10 minutes of silence with no in-progress work; a daily call limit exists. Start button hidden for subagents, archived chats, and Claude Code chats.

Developer Hands-on Guide

Update Cursor and sign in with an account (API-key-only sessions cannot start voice chat). When the agent is idle and the input is empty, click Start voice chat. The mic button remains dictation; Cmd+Shift+Space still toggles dictation in the IDE. Enable Privacy Mode for voice ZDR. Fix "Realtime voice requires sign-in" by completing account sign-in.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

Up NextCursor Design Mode adds Annotate: point, draw and edit text on your running app to send visual prompts to agents
Read Now→