SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18
Real-Time Voice Conversation
提供持续、流式或全双工的语音对话：语音输入、语音回复、唤醒词、打断、实时 turn-taking 和 agent 通话模式等输入输出闭环能力。单纯听写或朗读Plugin不属于此类。
Leaf membership
31 plugins
@muxiva/dsh-voice@muxiva/dsh-voiceCatalog AnalyzedLocal-first, full-duplex voice for DeepSeek Harness, orchestrated by MuxivaCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.0-alpha.1Evidence updated2026-09-09Public signals348 downloadsdeepseek-harness-voice-modeyankihue/deepseek-harness-voice-modeCatalog AnalyzedVoice mode for DeepSeek Harness: live captions, push-to-talk, spoken agent replies, barge-in, and real thread control via ElevenLabs.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-dictationdsh-dictationCatalog AnalyzedEditable local and desktop dictation for DeepSeek HarnessCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.0-beta.1Evidence updated2026-09-09Public signals163 downloadsdsh-edge-tts-chinesedsh-edge-tts-chineseCatalog AnalyzedVoice-first session loop for DeepSeek Harness, Chinese-first edge-tts focus (fork of dsh-talk): a composer microphone button with local/browser speech-to-text, speak replies aloud with edge-tts / local voices, and speak-to-interrupt.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-08Public signalsNo public usage signalsdsh-kitt-voicedsh-kitt-voiceCatalog AnalyzedDSH KITT — Spanish-first voice for the DeepSeek Harness web UI: hands-free conversation, push-to-talk (Whisper), read-aloud replies, and a floating overlay window with global hotkeys. · DSH KITT 语音：为 DeepSeek Harness 打造的语音Plugin——免提对话、按键说话（Whisper）、朗读回复，以及带全局CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact1.0.1Evidence updated2026-09-09Public signals0 downloadsdsh-live-voiceJstn-1g/dsh-live-voiceCatalog AnalyzedConsent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-plugin-dictatedsh-plugin-dictateCatalog AnalyzedLive speech-to-text dictation into the dsh web composer via OpenRouter STTCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-09Public signalsNo public usage signalsdsh-plugin-trtc-conaiDee3526/dsh-plugin-trtc-conaiCatalog AnalyzedTencent RTC Conversational AI (ConAI) voice agent tools for the DeepSeek HarnessCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-qwen-voiceleaveimagination/dsh-qwen-voiceCatalog AnalyzedVoice control and multi-session task dispatch for DeepSeek Harness, powered by Qwen Audio AgentCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-realtime-voicezfu691531-hash/dsh-realtime-voiceCatalog AnalyzedLightweight realtime ASR → DeepSeek Harness → TTS community plugin.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-realtime-voiceAlexKaiqi/dsh-realtime-voiceCatalog AnalyzedFull-duplex realtime voice-agent plugin for DeepSeek Harness, with OpenAI Realtime (WebRTC) and Doubao Duplex (WebSocket) adapters.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-realtime-voicemartinbear1/dsh-realtime-voiceCatalog AnalyzedRealtime full-duplex voice Agent plugin for DeepSeek Harness WebUI and future WeChat Mini Program clientsCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-talkdsh-talkCatalog AnalyzedVoice I/O for DeepSeek Harness — speech-to-text and text-to-speech over the microphone and audio output.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.3.4Evidence updated2026-09-06Public signals8 stars · 1286 downloadsdsh-voco@flowingspring/dsh-vocoCatalog AnalyzedContinuous voice conversations for DSH with hands-free listening, push-to-talk, speech recognition, TTS replies, and background Agent delegation.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.3.13Evidence updated2026-09-07Public signals1 stars · 1750 downloadsdsh-voicehaoku123/dsh-voiceCatalog AnalyzedFull-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals5 starsdsh-voiceJesse-njx/dsh-voiceCatalog AnalyzedVoice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), local-first under ~/.dsh/voice.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals4 starsdsh-voiceHarzva/dsh-voiceCatalog AnalyzedDSH plugin from Harzva/dsh-voiceCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-voice@goodandready/dsh-voiceCatalog AnalyzedVoice input for the web UI: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, or an OpenAI-compatible endpoint).CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.8.18Evidence updated2026-09-07Public signals2 stars · 3215 downloads
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.