DSH 专属语音输入插件：点按 Alt 说话、再点按转文字。默认本地离线识别（SenseVoice，零配置零 key、音频不出本机），自动回退浏览器 Web Speech，可选云端 ASR 与润色（复用 DSH 模型）。Voice input for DeepSeek Harness: tap Alt to talk, get text in the composer — local SenseVoice by default, zero config, zero API key.
Cross-referenced across 55 tracked directories
#9157
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
8/25/2026
Created
35
GitHub Stars
5
Forks
1,531
Weekly Downloads
10/27/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
matejmarinko-soniox
Soniox transcription provider for the Vercel AI SDK.
GitHub Actions
The **[Mistral provider](https://ai-sdk.dev/providers/ai-sdk-providers/mistral)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model, embedding model, and speech model support for Mistral APIs.
...moreGitHub Actions
The **[Deepgram provider](https://ai-sdk.dev/providers/ai-sdk-providers/deepgram)** for the [AI SDK](https://ai-sdk.dev/docs) contains transcription model support for the Deepgram transcription API and speech model support for the Deepgram text-to-speech
...more