← All guides

Gemini CLI voice mode

Gemini CLI voice can be cloud or local. Choose before speaking.

Gemini CLI now has an experimental Voice Mode with two different transcription paths. The default Gemini Live backend sends recordings to Google Cloud; the optional Whisper backend transcribes locally. IraVoice is useful only for a different job: one held-key Mac workflow across supported apps or a reusable brief you review before pasting.

Source-reviewed

1. Enable Gemini CLI’s native Voice Mode first

Use a current Gemini CLI release. Google’s release notes say real-time Voice Mode arrived in v0.41.0, and the current settings reference still marks it experimental and disabled by default.

Open /settings, find Voice Mode under Experimental, and enable it. Then run /voice in the interactive CLI. Native voice is the shortest path when the Gemini prompt itself is the destination; no separate Mac dictation app is required for that job.

  • Update Gemini CLI before looking for the setting.
  • Open /settings and enable experimental Voice Mode.
  • Run /voice in an interactive session.

2. Choose the transcription backend before speaking

The current default backend is gemini-live. Google’s settings reference explicitly says recordings using that backend are sent to Google Cloud for transcription.

Choose whisper when local transcription is the requirement. Keep the boundaries separate: local Whisper can keep microphone audio in the local transcription stage, but the resulting prompt still enters Gemini CLI and is processed under Gemini’s normal account, model, tool, and data controls.

3. Use push-to-talk or toggle recording deliberately

The default activation mode is push-to-talk. Hold Space while Voice Mode is active, speak, and release when the prompt is complete. Google exposes the app.voiceModePTT action in its keyboard-shortcut reference.

The alternate activation setting is toggle. Use it when holding Space is awkward for a longer requirement, then stop recording explicitly. In either mode, review the transcript before submitting agent instructions that contain commands, paths, permissions, numbers, or negations.

4. Match the local Whisper model to the job

Google currently exposes /voice model and a Whisper Model setting for the local backend. The documented choices range from smaller English-only models to quantized large-v3-turbo models.

A smaller model reduces the local footprint; a larger model can demand more storage and compute. Do not describe the backend as universally offline: model acquisition, Gemini authentication, and the later model request remain separate network and service boundaries.

5. Do not confuse transcription privacy with agent privacy

Voice transcription creates prompt text. Gemini CLI can then send that text, selected context, tool results, and later turns through the configured Gemini service. A local speech backend does not turn the whole coding agent into a local application.

Read the active workspace settings as well as the user settings because Google documents that workspace settings override user settings. That matters when a repository changes experimental.voice.backend or other Voice Mode behavior.

6. Add IraVoice only for the cross-app or brief workflow

Use Gemini CLI Voice Mode when you are already at its prompt and want either its cloud backend or its optional local Whisper path. Native input owns that destination and stays closest to the current CLI state.

Use IraVoice when the same held-key habit should work in supported email, notes, browser, and developer fields, or when a spoken requirement should become a reusable Markdown brief before you choose the destination. IraVoice has no direct Gemini CLI destination; review the focused-app or clipboard output and paste it into Gemini CLI yourself.

Decision guide

Native Gemini voice or IraVoice?

Choose based on the destination, transcription boundary, and artifact you need.

If you needChooseWhy
Speak directly into an active Gemini CLI promptGemini CLI /voiceIt is the native input path for the current interactive session.
Keep the speech-transcription stage localGemini CLI Whisper backendGoogle documents Whisper as the local transcription option.
Use Google’s hosted transcription backendGemini Live backendIt is the current default and sends recordings to Google Cloud.
Use one held-key workflow across supported Mac appsIraVoice DictateIt targets focused editable fields beyond one terminal agent.
Create reusable Markdown before choosing an agentIraVoice Voice-to-SpecThe reviewed brief can be pasted into Gemini CLI or another destination.

Primary sources

Use the current documentation.

This guide was reviewed July 26, 2026. Product versions, settings, policies, and availability can change.

  1. Gemini CLI: Settings

    Voice Mode enablement, activation modes, cloud and local backends, default values, model choices, and workspace-setting precedence.

  2. Gemini CLI: Keyboard shortcuts

    The current hold-Space push-to-talk action and interactive input controls.

  3. Gemini CLI: Release notes

    The v0.41.0 Voice Mode launch and later privacy and compliance UX updates.

Questions

What readers usually ask next.

Does Gemini CLI have voice input?

Yes. Google added experimental real-time Voice Mode in Gemini CLI v0.41.0. In a current release, enable Voice Mode under /settings, then run /voice in an interactive session.

Is Gemini CLI Voice Mode local?

It depends on the configured backend. The default Gemini Live backend sends recordings to Google Cloud for transcription. The Whisper backend transcribes locally, but the resulting prompt and later agent work still follow Gemini CLI’s normal service and tool boundaries.

How do I use push-to-talk in Gemini CLI?

With Voice Mode active and the default push-to-talk activation setting, hold Space while speaking and release it when finished. Toggle is the alternate activation mode for longer recordings.

Should I use IraVoice instead of Gemini CLI Voice Mode?

Use Gemini CLI’s native Voice Mode first when its prompt is the destination. IraVoice is the distinct option for supported cross-app Mac dictation or a reusable Markdown brief; it does not send directly to Gemini CLI.

macOS 26+ · Apple-silicon

Try the local Mac workflow for yourself.

Dictate ordinary text or turn a rough technical thought into reviewable Markdown during the 14-day full trial.