Voice Dictation for Devin Desktop (2026)

Devin Desktop is the new name for Windsurf: Cognition renamed the editor on June 2, 2026. Windsurf's built-in voice lived in Cascade, its agent chat, and Cascade is now a legacy agent that Devin Desktop no longer opens. Devin's own voice mode is a spoken call with the agent, not dictation. For dictation that works in the Devin Local prompt, the editor, the terminal, commit messages and every other app, and that is tuned to spell your code, use a system-wide layer like Aqua.

Devin's voice mode is useful when you want to talk a problem through: you start a call, you speak, and Devin answers out loud. It does not put text at your cursor, so it does not help you dictate a comment in the editor, a command in the integrated terminal, a commit message, or anything in an app outside Devin Desktop. A system-wide layer like Aqua inserts dictated text at your cursor anywhere in Devin Desktop and everywhere else, and it is tuned to get code identifiers right. If you want to talk with the agent, voice mode is fine. If you want to speak code, commands and prose across your whole machine, you want the system-wide layer.

That is the decision. The rest of this page explains what changed for voice when Windsurf became Devin Desktop, why an agent-first IDE makes dictation more valuable than ever, and how to set voice up so it works across all of Devin Desktop.

What changed for voice when Windsurf became Devin Desktop

Cognition bought Windsurf in July 2025 and renamed it Devin Desktop on June 2, 2026, as a regular over-the-air update. It is the same editor, with the same extensions, keybindings and settings. Two things changed for voice:

1. Cascade is now legacy. Windsurf's agent, Cascade, had a Voice input control that transcribed your speech into the agent chat. Devin Desktop no longer starts new Cascade conversations. Its local agent is now Devin Local.
2. Devin's voice mode is a call, not dictation. You start a voice call from the message box, talk, and Devin talks back. It is built for talking ideas through with the agent, not for putting text where your cursor is.

Neither of these puts dictated text in the editor, the integrated terminal, the commit box, the Command inline edit, or the other apps you touch in a day (browser, Slack, your notes, the PR description on GitHub). That was the gap Cascade's voice input left, and now it is the whole picture.

Why an agent-first IDE makes voice more valuable, not less

Devin Desktop's whole premise is that you steer agents. You describe intent in natural language, Devin Local writes, edits and refactors across files, and the Agent Command Center runs local and cloud agents side by side. That premise is exactly what makes voice pay off: the bottleneck is no longer how fast you type code, it is how fast you can express intent. Speaking is up to 5x faster than typing, and an instruction like "refactor the checkout flow to pull the tax logic out of CartSummary into a useTax hook, and update the tests" is far quicker said than typed.

But that same instruction is dense with the words general speech models are worst at: CartSummary, useTax, hook, the file paths, the library names. A model trained on audiobooks and podcasts hears "use tax" as two ordinary words. In a document you would skim past it. In an agent prompt, a mangled identifier sends the agent editing the wrong symbol, and now you are cleaning up instead of shipping. The faster the IDE lets you move, the more a general transcription engine costs you. This is the same reason we wrote up speech-to-text for Cursor and voice dictation for Claude Code: agent surfaces reward voice, and punish a model that cannot spell your codebase.

What "voice dictation for Devin Desktop" should actually do

For someone coding in Devin Desktop, dictation earns the label on four things:

1. Code-identifier accuracy. It writes useTax, tRPC, pnpm dlx, apps/web/src/routes and AuthContext as written, not as a phonetic guess. Aqua runs its own proprietary model, Avalon, trained on human-computer-interaction speech (prompts, code, commands and email) rather than audiobooks. In a 9to5Mac side-by-side against built-in macOS Dictation on the same passage, Apple made 17 errors and Aqua made 1.
2. Works everywhere in Devin Desktop, and outside it. One hotkey should insert text at the cursor in the Devin Local prompt, the editor, the integrated terminal, the Command inline edit, and the commit box, and then keep working the second you tab over to your browser, Slack or a GitHub PR. A system-wide layer does not care which surface has focus.
3. Context awareness. Aqua's Deep Context reads what is on screen, so when your editor is full of one project's names, transcription leans toward those terms instead of their English near-homophones.
4. Speed. Aqua inserts text about 450ms after you release the key. When you are firing quick prompts and short edits at an agent, that latency is the difference between staying in flow and waiting on your tools.

On independently checkable footing: Avalon placed #1 among proprietary models on the OpenASR leaderboard at its October 2025 debut. Aqua's own AISpeak benchmark, which we label self-reported, puts Avalon at 97.3% on AI and coding jargon versus far lower scores for general engines. Aqua also covers 49 languages and runs on Mac, Windows, iOS, and Android.

How to set up voice dictation across Devin Desktop

Because Aqua is an OS-level layer, there is nothing to install inside Devin Desktop and no per-panel config. You set it up once at the system level and it works in every Devin Desktop surface and every other app.

1. Install Aqua for macOS or Windows and sign in.
2. Grant accessibility / input permission when prompted so Aqua can insert text into other apps. On macOS this is System Settings > Privacy & Security > Accessibility.
3. Pick your push-to-talk key. The default is Fn (hold to record, release to insert). Hold-to-talk suits an IDE because your bursts are short: a prompt here, a variable name there.
4. Click into any Devin Desktop surface: the Devin Local prompt, a code file, the integrated terminal, the Command inline edit, or the commit message box.
5. Hold Fn, speak, release. The text lands at the cursor. Read it, then send or run.

That is the whole loop, and the same muscle memory works the instant you leave Devin Desktop for your browser, your terminal in another window, or Slack.

A real example in Devin Local

Open a Devin Local session, click into the prompt, hold Fn, and say:

"In useTax, memoize the rate lookup with useMemo keyed on the cart's country code, and add a unit test in useTax.test.ts covering a zero-rate region."

Release, and the full instruction lands in the prompt box, useTax, useMemo and useTax.test.ts intact, then you hit send. No reaching back to fix a mangled hook name. The same hold-Fn habit works when you drop into the editor to dictate a docstring or into the terminal to talk to a CLI agent.

Dictating code accurately: a few habits

Voice is for intent, not for spelling out every character. A few habits make Devin Desktop smooth:

• Speak identifiers naturally. Say "use tax hook" or "auth context" and let a code-tuned model resolve the casing. For the exact spelling of an oddly-cased symbol, add it to your dictionary once (below) rather than fighting it every time.
• Let the agent resolve boilerplate. In Devin Local, describe the goal ("extract the tax logic into its own hook and wire it into CartSummary") instead of narrating syntax. The agent writes the code; you supply the intent.
• Add your constants to the Custom Dictionary. Repo names, internal libraries, service names, model names, a teammate's handle (up to 800 entries on Pro) so they are locked in every time.
• Use Custom Instructions for standing preferences, for example "keep commit messages in the conventional-commits format" or "prefer TypeScript over JavaScript in examples."

You will still type the occasional exact token, and that is fine. Most of what you send an agent is reasoning and instruction, which is what voice is fastest at.

Devin's voice mode vs a system-wide layer: which should you use?

A fair, honest split:

• Use Devin's voice mode if you want to talk a problem through with the agent and hear it answer, and you do not need your words typed at the cursor.
• Use a system-wide layer like Aqua if you want to dictate across every Devin Desktop surface and every other app, you want higher accuracy on symbol names, library names and file paths, and you want one hotkey and one habit everywhere.

One honest caveat on Aqua: it is cloud-based, so it needs a network connection. On a fully offline machine, a local tool wins. For everyday connected work, the code accuracy and the everywhere-reach are worth the trade.

On price, Aqua Pro is $10/mo billed annually, with a free Starter tier (2,000 words) to try it and a 70% student discount when you sign up with your university or college email. If you want to build voice into your own tooling, the Avalon API is an OpenAI-compatible endpoint at $0.39 per hour of audio. See how Aqua stacks up against Wispr Flow, and the full feature tour is in the Aqua guide.

The bottom line

Windsurf's voice lived in one panel, and that panel is now legacy. Devin Desktop is built around steering agents, which is precisely where speaking beats typing, because the work is expressing intent, not pressing keys. That value only fully lands when voice follows you into the agent prompt, the editor, the terminal, the commit box and every app after it, and when the model can actually spell your codebase. We have typed for 150 years. In an IDE you increasingly talk to, it is time to speak.

FAQ

Is Devin Desktop the same as Windsurf? Yes. Cognition renamed Windsurf to Devin Desktop on June 2, 2026, through a regular update. Your plan, settings and extensions carried over, and Aqua works in it the same way it did in Windsurf.

Does Devin Desktop have built-in voice input? Windsurf's voice input was part of Cascade, which is now a legacy agent in Devin Desktop. Devin's voice mode lets you talk with the agent in a voice call, but it does not type into the editor, the integrated terminal, commit messages, or other apps.

What is the most accurate voice dictation for Devin Desktop? Accuracy on code identifiers, library names and file paths is what decides it. Aqua runs its own Avalon model, trained on prompts and code rather than audiobooks, and placed #1 among proprietary models on the OpenASR leaderboard at its October 2025 debut. In a 9to5Mac test it made 1 error where macOS Dictation made 17.

Can I dictate in the Devin Desktop editor and terminal, not just to the agent? Yes, with a system-wide layer. Aqua inserts text at the cursor in the Devin Local prompt, the editor, the integrated terminal, the Command inline edit and the commit box, and in every app outside Devin Desktop, all from one push-to-talk key.

How much does Aqua cost for Devin Desktop users? Aqua Pro is $10/mo billed annually, with a free Starter tier (2,000 words) and a 70% student discount when you sign up with your university or college email. There is also an Avalon API at $0.39 per hour of audio for building voice into your own developer tooling.