speech-recognition

TypeScript library for building multimedia-generation agents: text-to-image, video, speech and audio pipelines with capability-based model routing, automatic cross-model fallback, and BYOK direct provider calls (no gateway). 27 built-in patterns, provider-SDK-free core.

Persistent voice conversations for DSH with cloud speech recognition, Edge TTS, and background Agent delegation.

DeepSeek Harness client plugin: mic dictation button next to the Full access control

dsh全模态工作站插件，让模型支持视频、图片、语音的输入与输出，支持comfyui图像生成工具调用。Any-to-Any.

Speech plugin for DeepSeek Harness: per-message voice playback, auto-announce, and dictation via mic — cloud TTS/ASR on Alibaba DashScope or Volcengine (freely combinable), with Web Speech API fallback.

Voice-to-text for the DeepSeek Harness Web UI — live, editable, never auto-sends. | DeepSeek Harness 网页语音输入

DSH Web 中英语音输入插件，支持中英混合口述，基于浏览器 Web Speech API。 Chinese and English voice input for DSH Web, with mixed-language dictation via the browser Web Speech API.

Local voice typing and speech-to-text plugin for DeepSeek Harness (dsh), powered by multilingual Whisper.