Feature Request: Native voice dictation for Copilot Chat in VS Code is urgently needed #190615
Replies: 1 comment
-
|
💬 Your Product Feedback Has Been Submitted 🎉 Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users. Here's what you can expect moving forward ⏩
Where to look to see what's shipping 👀
What you can do in the meantime 💻
As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities. Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐ |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
🏷️ Discussion Type
Product Feedback
💬 Feature/Topic Area
RED ALERT: Voice Input / Dictation for GitHub Copilot!
Body
Today, the built-in path for speech in VS Code relies on the VS Code Speech extension, which Microsoft describes as the speech-to-text layer for chat in VS Code. But in practice, the experience is not strong enough for serious day-to-day use. There are multiple public bug reports around voice input reliability, including cases where no speech is converted at all.
The bigger issue is accuracy. For real development workflows, the current experience is effectively unusable when dictating technical prompts, code-related language, file names, symbols, and longer instructions. That forces me to leave VS Code and GHCP, dictate into other AI tools with better voice input, and then paste the result back into Copilot. That breaks flow and slows everything down.
Meanwhile, the market is moving fast. Developers are already building voice-first workflows around newer coding agents and tools like Codex and Claude Code because the underlying interaction model is getting much closer to what they actually want: fast, natural, high-trust input directly into the coding loop. Copilot should lead that shift, not trail it.
Whisper-style transcription raised the bar on what good speech input looks like: stronger handling of accents, background noise, long-form speech, and technical language. That is the level of quality developers now expect.
That gap is the real problem. This should not be a workaround category solved by extensions and copy-paste. It should be a first-class Copilot capability.
What I want is native, high-accuracy dictation directly inside GitHub Copilot Chat in VS Code, with strong handling of technical language, punctuation, file paths, symbols, and long prompts. Push-to-talk and continuous dictation modes would both be valuable.
Developers are already proving demand for voice-first coding workflows, and competing tools like Codex and ClaudeCode make that future feel closer, not farther away. Copilot should be defining that experience.
Beta Was this translation helpful? Give feedback.
All reactions