产出画廊：图片 / 文件 / 音视频实时可见、当场校验；原生产出标签（素材 / 过程稿 / 定稿 / 未归类）可手动改且持久生效，改标签动作与图上圈选批注攒进反馈篮，由人审核合并后发送，全程零自动发送；视频「截取当前帧」自动存入当前对话资产，反馈能精确指到某一帧；批注框跟随图片缩放平移，标注态按住鼠标中键可平移且框不脱框。Output gallery for DeepSeek Harness: live image/file/audio/video preview, persistent manual a
Cross-referenced across 55 tracked directories
#9465
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
11/3/2026
Created
1
GitHub Stars
3,552
Weekly Downloads
11/11/2026
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
...moreGitHub Actions
The **[ElevenLabs provider](https://ai-sdk.dev/providers/ai-sdk-providers/elevenlabs)** for the [AI SDK](https://ai-sdk.dev/docs) contains speech generation plus batch and realtime transcription support for the ElevenLabs APIs.
...more