diff --git a/docs/internals/voice-input.md b/docs/internals/voice-input.md index 55e3007a48721..f678b5697977e 100644 --- a/docs/internals/voice-input.md +++ b/docs/internals/voice-input.md @@ -2,7 +2,7 @@ Transcription edits a composer draft. It does not submit an agent turn. Audio is temporary client input, and only normal message submission sends the resulting -text. The current implementation transcribes locally on supported iOS devices; +text. The current implementation transcribes locally on supported iOS and Android devices; environment-backed transcription is not implemented. The [shared controller](../../packages/client-runtime/src/voice-input/controller.ts) diff --git a/docs/user/faq.md b/docs/user/faq.md index 6f4a02e485bb0..d1c4b73f98825 100644 --- a/docs/user/faq.md +++ b/docs/user/faq.md @@ -77,7 +77,7 @@ Open **Settings > Storage** and turn on automatic worktree cleanup. You can also ## Is there voice input? -On iPhone, yes. You need iOS 26 or later. Tap the mic in the composer, talk, check the text, then send. Web, desktop, and Android do not have it yet. [Voice input on iPhone](./composer.md#voice-input-on-iphone) +On supported iPhones with iOS 26 or later and Android devices with Android 12 or later, yes. Android also needs compatible on-device speech services. Tap the mic in the composer, record, confirm to transcribe, check the text, then send. Web and desktop do not have it yet. [Voice input on mobile](./composer.md#voice-input-on-mobile) ## Does it work on Windows, Mac, and Linux?