GitHub Copilot CLI voice input

Copilot CLI has local voice input. Start there.

GitHub Copilot CLI can now transcribe spoken prompts entirely on your machine and insert editable text at its own prompt. IraVoice is useful only for a different job: one held-key Mac workflow across apps or a structured brief you review before pasting into Copilot.

Source-reviewedReviewed July 26, 2026

1. Use Copilot CLI’s native voice input first

Install or update GitHub Copilot CLI, start an interactive session with copilot, and authenticate if required. GitHub says the CLI is available with all Copilot plans; organization-provided access also depends on the organization’s Copilot CLI policy.

Run /voice. On first use, choose Continue to download the voice runtime, then download and activate the English or Spanish speech-to-text model. The runtime download can continue in the background while you use the CLI.

Start an interactive copilot session.
Run /voice and download the voice runtime.
Download and activate the intended English or Spanish model.

2. Hold Space for short prompts

Hold the Space bar until recording begins, speak the prompt, and release Space. Copilot CLI transcribes the audio and inserts the recognized text at the cursor in the prompt area.

The text is not submitted merely because transcription finished. Read it first, especially when names, paths, commands, negations, or permissions could change what the coding agent does.

3. Toggle recording for a longer requirement

Press Control-X followed by V to start a longer recording. Speak the requirement, then press any key to stop and insert the transcription.

GitHub also documents /refine for removing filler, applying self-corrections, fixing grammar, and grouping related points. Treat local speech recognition and subsequent Copilot processing as separate boundaries: GitHub’s local claim covers transcription, not every action taken after the text enters the agent prompt.

4. Switch the microphone or language deliberately

Run /voice devices to choose another available microphone. Run /voice models to download or activate a different speech model.

GitHub currently documents English and Spanish dictation only, with English as the default. The active model and voice-enabled state are stored in Copilot CLI settings, typically under ~/.copilot/settings.json.

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

Use Copilot CLI voice input when you are already at its prompt: it is native, local for transcription, and gives you editable text before submission. No separate Mac dictation app is needed for that job.

Use IraVoice when the same held-key dictation habit should extend to supported email, notes, browser, and developer fields, or when a spoken requirement should become a reusable Markdown brief before you choose the destination. IraVoice does not have a direct GitHub Copilot destination; review the focused-app or clipboard output and paste it into Copilot CLI yourself.

Decision guide

Native Copilot voice or IraVoice?

Choose the tool that owns the destination and the artifact you need.

If you need	Choose	Why
Speak directly into an active Copilot CLI prompt	Copilot CLI /voice	It is native to the prompt and GitHub documents local transcription.
Record a longer Copilot CLI requirement without holding a key	Control-X, then V	The native toggle records until the next key press.
Remove filler from the current Copilot prompt	Copilot CLI /refine	GitHub documents it as the native cleanup step for voice-entered text.
Use one held-key workflow across several Mac apps	IraVoice Dictate	It targets supported focused editable fields beyond one terminal agent.
Create reusable Markdown before choosing an agent	IraVoice Voice-to-Spec	The reviewed brief can be pasted into Copilot CLI, Codex, Claude Code, or a document.

Primary sources

Use the current documentation.

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

GitHub Docs: Use voice input with Copilot CLI ↗
Local transcription, audio boundary, setup, shortcuts, models, microphones, language limits, settings, and refine workflow.
GitHub Docs: Using GitHub Copilot CLI ↗
Current plan availability, organization policy, interactive setup, authentication, trust, prompts, and tool approvals.
GitHub: The agent-native desktop experience ↗
GitHub’s June 2026 product announcement describing Copilot CLI voice mode and on-device speech-to-text.

Questions

What readers usually ask next.

Does GitHub Copilot CLI have voice input?

Yes. In an interactive Copilot CLI session, run /voice to download and enable the voice runtime and a speech model. You can then hold Space for short prompts or use Control-X followed by V for toggle recording.

Is GitHub Copilot CLI voice input processed locally?

GitHub’s current documentation says transcription runs entirely on the local machine and audio is not sent over the network. The resulting prompt and later agent work still follow GitHub Copilot’s normal service, account, and permission boundaries.

Which languages does Copilot CLI voice input support?

GitHub currently documents English and Spanish dictation. English is the default, and the active model can be changed with /voice models.

Should I use IraVoice instead of Copilot CLI voice input?

Use Copilot CLI’s native voice input first when that 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 GitHub Copilot.

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.

Start 14-day trial $50 once