← All guides

Windsurf and Devin Desktop voice input

Windsurf voice works in Cascade. That is not editor-wide dictation.

Current Windsurf documentation URLs redirect to Devin Desktop documentation, where Cascade has a Voice input control that transcribes speech to text. That native path is the shortest route into Cascade. Dictating into a code buffer, terminal, commit message, or another Mac app is a separate system-wide text-input job.

Source-reviewed

1. Follow the current Windsurf documentation redirect

The former Windsurf Cascade documentation URL now redirects to the current Devin Desktop Cascade page. That page describes Cascade as the agentic assistant in Devin Desktop and documents Voice input as one of its features.

Use the current documentation rather than an older screenshot or tutorial because the product name, setup, controls, and availability can move during this transition. One guide owns both Windsurf and Devin Desktop search intent instead of publishing duplicate pages for the same evolving product.

2. Use native Voice input when Cascade is the destination

Open Cascade with Command-L or the current Cascade control, choose the intended Code or Chat conversation, then use the visible Voice input control. The official page says the feature can transcribe your speech to text.

Native voice is the most direct option when you are already speaking to Cascade. It keeps the transcript attached to the active conversation and avoids adding another input layer for that one surface.

  • Confirm the repository and active Cascade conversation.
  • Speak one bounded requirement.
  • Review the transcript before the agent receives ambiguous names, paths, commands, numbers, or negations.

3. Keep Cascade voice separate from editor-wide text input

The official Cascade page scopes Voice input to interacting with Cascade. It does not describe that control as a voice keyboard for the code editor, integrated terminal, commit-message field, browser preview, or other applications.

For another Mac text field, click until the insertion point is visible and use the Dictation shortcut shown under System Settings → Keyboard. Apple says Dictation can enter text anywhere you can type, subject to the current field, language, Voice Control, microphone, and processing configuration.

4. Do not invent a privacy claim the voice page does not make

The current Cascade overview says Voice input transcribes speech to text, but the reviewed page does not identify the speech processor, transmission path, retention rule, or a local-only mode for that audio. Do not label it local or cloud from the interface alone.

Keep transcription and agent processing separate. Even if one speech stage were local, the resulting prompt, selected text, repository context, tool calls, and model work would still follow the active Devin Desktop account, model, and service controls.

5. Review speech before Cascade can act on it

A voice transcript in an agent prompt can become more than prose. Cascade Code mode can edit files and call tools, while Chat mode can propose code. A misheard path, package, flag, permission, or destructive verb can materially change the task.

Use a visible review step before submission. If the request is long, speak the goal, constraints, acceptance criteria, and exclusions as separate points rather than one unstructured paragraph.

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

IraVoice 0.7.1 is a separate option for macOS 26+ Apple-silicon Macs when one held-key workflow should produce editable text across supported developer, email, document, and browser fields. Speech recognition and supported formatting run on the Mac after model setup.

Use Dictate for ordinary prose in a supported focused field. Use Voice-to-Spec when a spoken requirement should become reviewable Markdown before it reaches an agent. IraVoice does not control Cascade, read the repository on Windsurf’s behalf, dictate reliable source syntax, press Send, or bypass the destination’s account and tool permissions.

Decision guide

Which Windsurf voice path fits the field?

Choose the input owner and the review boundary before speaking.

If you needChooseWhy
Speak directly into the current Cascade conversationCascade Voice inputIt is the native speech-to-text path documented for that agent surface.
Dictate prose into another editable Mac fieldmacOS DictationApple documents it as the included text-input path anywhere you can type.
Keep speech recognition on a compatible MacIraVoiceIraVoice documents on-device recognition; the current Cascade voice page does not claim local speech processing.
Create a reusable Markdown requirement before choosing an agentIraVoice Voice-to-SpecIt creates a reviewable artifact rather than speaking directly into one live Cascade conversation.
Dictate exact source code or execute terminal syntaxType and review the syntaxNeither path should be treated as a deterministic source-code or shell-command generator.

Primary sources

Use the current documentation.

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

  1. Devin Desktop: Cascade overview

    Current Cascade identity, Code and Chat modes, Command-L access, tool calling, Voice input, checkpoints, and real-time awareness.

  2. Devin Desktop: Getting started

    Current product naming, Mac, Windows and Linux setup, account requirement, command palette, and Windsurf migration paths.

  3. Apple: Dictate messages and documents on Mac

    Current focused-field Dictation workflow, shortcut, language, Voice Control interaction, microphone choice, and processing-disclosure guidance.

Questions

What readers usually ask next.

Does Windsurf have built-in voice input?

The current official documentation, now under Devin Desktop, says Cascade has Voice input that transcribes speech to text. Use it when the Cascade conversation is the destination.

What happened to the Windsurf Cascade documentation?

The former Windsurf Cascade URL currently redirects to the Devin Desktop Cascade documentation. This guide uses that current canonical source rather than treating the renamed surfaces as two separate products.

Does Windsurf voice input work everywhere in the editor?

The reviewed official page scopes Voice input to interacting with Cascade. It does not document the same control as editor-wide dictation for code buffers, terminals, commit messages, or other apps.

Is Windsurf or Devin Desktop voice input processed locally?

The current Cascade overview reviewed here does not say. It documents speech-to-text behavior without naming the voice processor, transmission path, retention rule, or a local-processing guarantee.

Can IraVoice send a specification directly to Windsurf?

No. IraVoice has no direct Windsurf or Devin Desktop destination. Use focused-app delivery or the clipboard, review the text, and paste it into the intended Cascade conversation yourself.

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.