SenseVoice API
SenseVoice API is an OpenAI-compatible speech-to-text API that wraps SenseVoice-Small to provide low-latency transcription with automatic language…
Platform availability
Available on 1 of 10 platforms
- Unraid
- TrueNAS (not listed)
- Umbrel (not listed)
- ZimaOS (not listed)
- Proxmox (not listed)
- Helm (not listed)
- Mac (not listed)
- Windows (not listed)
- Linux (not listed)
- Any server (not listed)
Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.
34/100 Low
- Maintained
- 60last commit 149 days ago
- Popular
- 61 GitHub stars
- Easy to install
- 351 install platform, install notes, Docker image
- Light to run
- 1016 GB minimum RAM
Availability: platform listings confirmed today, links checked 18 days ago
- GitHub stars
- 1
- Open issues
- 0
- Last commit
- 2026-06-25
- Activity
- stale
Checked 6 days ago - source: GitHub (hsiang-han/SenseVoice-API)
Resources & Compatibility
Minimum requirements: 16 GB RAM.
Checked 54 days ago - source: Docker Hub image tags and published docs
First-install notes
- Start it with Docker Compose Run `docker compose up --build` to build and start the SenseVoice stack; without this, the API has no running service. CPU is the default unless you change the device setting. source
- Keep the model storage area safe The Docker setup uses the sensevoice-models volume (a Docker storage area for model files), so keep it if you want faster startup and avoid re-downloading. Deleting it can leave the app without the models it needs. source
- Set the device for FastAPI port 50000 If you want to use a GPU, set SENSEVOICE_DEVICE=cuda:0 before running `fastapi run --port 50000`. Without that setting it may stay on CPU, and if port 50000 is blocked API clients cannot connect. source
- CPU-only mode For CPU-only operation, set DEVICE to cpu and remove --gpus all from Extra Parameters. source
Fetched 48 days ago - each note links to its source
Variants
Alternatives
No alternatives collected yet.
Common questions
Can existing OpenAI SDK audio transcription code point to SenseVoice-API?
Yes, use the local v1 endpoint on port 10095, request model sensevoice-small, and set the API key to none.
How do I get word-level timestamps, emotion, and audio event labels?
Send response_format=verbose_json with the transcription request. The response includes language, duration, emotion, event, processing time, and per-word start and end times.
Does SenseVoice-API support WebSocket streaming?
Yes, connect to the stream endpoint on port 10095 and send audio bytes. It returns a JSON result with text, language, emotion, event, and is_final.
How do I enable speaker diarization?
Set ENABLE_SPK=true, which uses the cam++ model. The verbose response then includes segments with speaker IDs, start and end times, text, and emotion.
Can SenseVoice-API run without a GPU?
Yes, use CPU-only mode by setting DEVICE to cpu and removing --gpus all from the container parameters.
How do I avoid re-downloading the model after container recreation?
Mount a persistent directory to /root/.cache/huggingface so the approximately 900MB model download is reused on later starts.
Answers sourced from github.com
Community
Collected 49 days ago - public community threads