[MNNChat:Feature] Implement real-time vision capabilities for interactive voice chat. Enable "ChatGPT-like" real-time visual dialogue by sending captured frames to LLM.#4263
Merged
wangzhaode merged 3 commits intoalibaba:masterfrom Mar 16, 2026
Conversation
- Keep ASR recording active during LLM generation and greeting playback. - Add speech detection listener to interrupt AI output when user starts speaking. - Improve responsiveness by allowing users to skip/interrupt AI responses.
…tion function. - Support software-based echo cancellation (Auto-Mute mode) - Automatically mute mic when AI starts speaking/generating - Automatically unmute mic when AI finishes speaking or is interrupted - Maintain full-duplex interruption support in hardware AEC mode - Refine code comments to clarify speech interruption and ASR state logic
JedLee6
changed the title
…tive voice chat. - Support live camera preview with front and back camera switching. - Integrate CameraX for high-performance, low-latency image capture. - Optimize image processing by combining scaling and rotation into a single operation. - Enable "ChatGPT-like" real-time visual dialogue by sending captured frames to LLM. - Add comprehensive Javadoc and documentation for all vision and image utility logic.
JedLee6
force-pushed
the
jedlee/ft/master_260316
branch
from
81b2409 to
47cb56d
Compare
JedLee6
changed the title
JedLee6
changed the title
Juude
approved these changes
Mar 16, 2026
Juude
added a commit
to Juude/MNN
that referenced
this pull request
Mar 16, 2026
…moke test Cherry-picked from pr-4263 (commit 47cb56d) with additional fixes: - CameraX integration for live camera preview in VoiceChatFragment - Vision mode: capture and send photos during voice chat - Camera toggle button (on/off) with front/back switch support - ImageUtils for image scaling and rotation optimization - VoiceChatPresenter: add muteMicrophone() helper method - Smoke test: 19_regress_vision_chat_ui.sh for E2E verification Tested on device 1b4a0523: - All 9/9 smoke test checks PASS - Camera preview, toggle, switch all functional - Echo cancellation mode preserved 🤖 Generated with [Qoder][https://qoder.com]
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
😃 Hi, @wangzhaode @Juude . Could you please review and merge the following Pull Request at your convenience? Thanks! This PR Implement real-time vision capabilities for interactive voice chat. Enable "ChatGPT-like" real-time visual dialogue by sending captured frames to LLM.
video6174455438680005488.mp4
Key Changes: