4 results
Voice input for DeepSeek Harness Web UI: a mic button in the composer tool row that uses the browser's Web Speech API (Chrome/Edge) to transcribe speech directly into the message draft. Zero dependencies, no API keys.
dsh auto-vision bridge: paste an image into a text-only model's composer and a configured multimodal model transcribes it as text, automatically.
MiniMax speech-to-text (asr-1.0) and text-to-speech (speech-2.8-hd) as a global DeepSeek Harness plugin: a transcribe_audio tool, an announce_speech tool, a settings card, composer voice input, spoken turn announcements, and handsfree conversation.
Voice for DeepSeek Harness backed by Xiaomi MiMo: browser-native ๐ค/๐ UI (MiMo TTS read-aloud) + voice_transcribe/voice_speak calling MiMo ASR/TTS directly, with a configurable voice map and in-conversation speech strips. Fork of zhuiyueya/dsh-voice (MIT).