asr 9

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Voice input plugin for DeepSeek Harness

Full-duplex voice mode for DeepSeek Harness: zipformer2 streaming ASR → editable draft, Edge TTS sentence-by-sentence read-aloud with live captions, true barge-in — on-device ASR, no API key. · DSH 语音双工对话：流式识别入草稿、按句朗读+实时字幕、开口即打断，识别本地推理、无需 API Key

Context-aware voice input for DeepSeek Harness with Web Speech, local SenseVoice transcription, model polish, editable Composer drafts, and user-controlled sending

聊天框语音输入按钮 for DeepSeek Harness: 点击麦克风说话,多引擎转写(智谱 GLM-ASR-2512 / 本地 faster-whisper / Gemini / OpenAI)自动填入输入框。一个按钮,所见即所得。

Animate any photo into a responsive virtual girl. She talks, turns, smiles, and moves naturally in sync with your conversation. Low-lag, high-detail.

Tencent Cloud ASR voice input for DeepSeek Harness: composer mic + live preview + settings card, installed as a pure pluggable bundle (no core changes)

MiMo (Xiaomi) tools as a DSH profile plugin: web search, image/audio/video understanding, ASR transcription, TTS, voice design and voice cloning — native agent tools with a Settings page for the API key.

SenseVoice 语音输入插件 for DeepSeek Harness：在对话输入框旁添加麦克风按钮，录音后调用本地 SenseVoice 服务转成文本填入输入框。首次使用自动下载模型并显示进度，后端由插件自动启动。