10 results
DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text before delegating to the text-only DeepSeek adapter. Official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), any OpenAI-compatible VLM or local Ollama as alternatives, never hangs.
Composer mic for DeepSeek Harness Web: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.
Voice input plugin for DeepSeek Harness
Context-aware voice input for DeepSeek Harness with Web Speech, local SenseVoice transcription, model polish, editable Composer drafts, and user-controlled sending
Multi-provider image, video, and speech generation, transcription, visual understanding, and prompt optimization with an integrated Iris workbench for DeepSeek Harness.
DeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.
Speech capability plugin for the DeepSeek Harness (dsh) web host: a token-gated /s/api route family serving audio transcription (ASR) and synthesis (TTS) over configurable providers
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.
DSH plugin: speech-to-text input via microphone or file upload, transcribed through an OpenAI-compatible /v1/audio/transcriptions endpoint.
DSH plugin (DeepSeek vision bridge): give text-only agents vision through chat.deepseek.com's unofficial vision mode — WeChat-QR/password login in Settings, a deepseek_vision model tool, and automatic in-chat image transcription.