[FEATURE]: Speech-to-Text Voice Input for Lazy People in OpenCode

Feature hasn't been suggested before.

I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

Hi! First of all, congratulations on the amazing project.

I've been working on a Speech-to-Text voice input feature that integrates directly into the TUI. It allows users to start audio recording with a keybind, automatically transcribe speech using different providers, and insert the resulting text directly into the prompt.

I've built an initial working version, currently tested only on macOS, and the system includes:

Real-time audio recording via FFmpeg;
Support for Groq Whisper, OpenAI Whisper, and local whisper.cpp;
Automatic microphone/device detection;
Interactive menus for choosing provider, model, and audio device;
Persistent configuration stored in ~/.opencode/state/speech.json;
Customizable keybinds (Ctrl+X v, Ctrl+X P, Ctrl+X D);
Smooth flow: record → transcribe → insert into prompt input;

Would this be something you'd be interested in integrating into the project?

That sounds cool, did you integrate it using the plugin system, and if not why? Maybe we need to expand it to allow for stuff like this

This ticket inspired me to create this:
https://github.com/chuckstack/groq-whisper

This is not nearly as good or integrated as what is described above; however I could not wait for the above to be accepted. I thought you would appreciate seeing a generic tools approach to implementing it.

You can use it from:

opencode: !groq-whisper # this injects the response directly into the context without the ability to edit prior to injection
vim: :r groq-whisper # this allows you to ctrl+p => open editor (vim) and capture the text before submitting
terminal: groq-whisper # can be used outside of opencode

I hope this helps!

edit to above details:

only tested on debian (see notes for mac)
only uses groq whisper

would be really awesome !

I was just looking for something like this today, it'd be awesome to see it implemented!

bump for interest!

Hey! Same here! I'd love it!

hi, checkout another implantation #9264 support both whisper model and audio large language model (gpt-4o, qwen3-omni, etc.)

This could be really interesting if it were part of the web version. OpenCode isn’t just a dev tool anymore — plugins for meeting notes or a knowledge base would be awesome.

Need this!

@Fuzu

@Fuzu I'm interested in this. Do you think you can make you changes available for us people who want to use it in a different repo? At least until this gets sorted out if it will become an official part of opencode.

I use an external app for this (Raycast + Whisper Dictation) and works great, except that you can't see or edit the transcribed text. That's why I think this is necessary:

I just created a implemetation for this in #11345. This works without the need for any api keys. The edited text also appears right away without the [Pasted x lines].

I know some people can't wait for this feature so here is how to use it locally; Clone my opencode fork linked in the PR, bun install and add the following to your .bashrc:

opencode-dev() {
    local cwd="$PWD"
    bun run --cwd /path-to-repo/packages/opencode --conditions=browser ./src/index.ts "$cwd" "$@"
}

Then u can run opencode-dev to start.

Would be awesome - also for the IDE / desktop version.

please merge this!

If you're on linux I found this application useful: https://www.speedofsound.io/

Any advantages over handy? I've been using handy extensively across platforms.

…

On Thu, 7 May 2026, 13:57 Emad Elsaid, ***@***.***> wrote: *emad-elsaid* left a comment (anomalyco/opencode#4695) <#4695 (comment)> If you're on linux I found this application useful: https://www.speedofsound.io/ — Reply to this email directly, view it on GitHub <#4695 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AGDNFLRDXAOV7S2WNL7YQVD4ZSB4HAVCNFSM6AAAAACNBZ3KWOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHM2DGOJXGI4TEMJSGU> . You are receiving this because you commented.Message ID: ***@***.***>

@luqs1

@luqs1 looks the same to me

voice is the new vibe, openCode needs to catch up :)

Seems like this is either a paywall or dead end, i ended up creating and hardenend Docker sandbox in which i connect remotely via SSH ( https://github.com/jammsen/docker-opencode-sandbox ) and im using Handy ( https://github.com/cjpais/Handy ) with it to have the same thing. Works awesome and is only like 5-10 minutes setup.

#30601 (comment) see also

#29663 see also, much better accuracy

https://github.com/theoparashkevov/opencode-talk

Mortic — voice control for the agent already in your OpenCode thread

Hey everyone — I’m building Mortic, a voice interface designed specifically for OpenCode.

Instead of introducing another assistant, Mortic lets you speak to the agent already working inside your coding thread. You can brainstorm, ramble through an idea, explain a bug, or correct the task naturally while preserving the existing files, decisions, and conversation context.

The goal is:

Natural voice input for longer or less-structured thoughts
No context reset and no second assistant
Spoken answers for the explanation
Code, commands, paths, JSON, and diffs kept exact on screen
A terminal-native interface that feels like part of OpenCode

I have a working demo and I’m currently collecting signups for a private beta:

https://mortiphi.com/

I’d really value feedback from OpenCode users:

Would you use voice during a coding session?
Where would it be most useful—or most annoying?
What would Mortic need to do before you’d try it?

This is still early, so honest criticism is very welcome.

@rekram1-node

@rekram1-node @simonklee

This feature request has garnered quite a bit of attention from the community. However, this thread is marked as “Not planned.”
What is the roadmap for this?

Is the only way to get this functionality (which, let's be honest, will be needed by a huge number of developers in the near future) to use a third-party library or build a plugin yourself?

They're only using bots and there's no project manager on this project. Just GitHub automations that are shutting down major features; they're losing their community that way.

https://x.com/thdxr/status/2082825101263732984

opencode v2 I guess

Navigation Menu

Repository navigation

[FEATURE]: Speech-to-Text Voice Input for Lazy People in OpenCode #4695

Feature hasn't been suggested before.

Describe the enhancement you want to request

12 remaining items

Mortic — voice control for the agent already in your OpenCode thread

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

[FEATURE]: Speech-to-Text Voice Input for Lazy People in OpenCode #4695

Description

Feature hasn't been suggested before.

Describe the enhancement you want to request

Activity

rekram1-node commented on Nov 25, 2025

cboecking commented on Nov 25, 2025

sfpmld commented on Dec 29, 2025

nanoandrew4 commented on Jan 12, 2026

0x7C2f commented on Jan 15, 2026

KristjanMinn commented on Jan 17, 2026

heimoshuiyu commented on Jan 18, 2026

WillianQ commented on Jan 26, 2026

kwakubiney commented on Jan 26, 2026

kenthinson commented on Jan 28, 2026

berenar commented on Jan 28, 2026

cmdNiels commented on Jan 31, 2026

gimlichael commented on Feb 10, 2026

AliRezaei-Code commented on Feb 18, 2026

12 remaining items

emad-elsaid commented on May 7, 2026

luqs1 commented on May 7, 2026

emad-elsaid commented on May 7, 2026

cmadden-cirqul commented on May 22, 2026

jammsen commented on May 23, 2026

alexandre-leng commented on Jun 3, 2026

heimoshuiyu commented on Jun 4, 2026

theoparashkevov commented on Jun 5, 2026

Aeroknight786 commented on Jul 17, 2026

Mortic — voice control for the agent already in your OpenCode thread

Hakenadu commented on Jul 18, 2026

alexandre-leng commented on Jul 18, 2026

Hakenadu commented on Aug 3, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions