Issue Station
Sign In
Tools hereToolbox

litellm - 💡(How to fix) Fix Feature request: Add FunASR as STT provider (OpenAI-compatible)

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Code Example

# User configuration
litellm.transcription(
    model="funasr/sensevoice-small",
    file=audio_file,
    api_base="http://localhost:8000"
)

---

pip install funasr vllm fastapi uvicorn python-multipart
funasr-server --device cuda --port 8000
# POST /v1/audio/transcriptions ready
RAW_BUFFERClick to expand / collapse

Feature Request

Add FunASR as a speech-to-text provider in LiteLLM.

Why

LiteLLM already supports 100+ LLM providers. For STT, FunASR provides a self-hosted, OpenAI-compatible endpoint:

  • OpenAI-compatible API: funasr-server serves POST /v1/audio/transcriptions — same format as OpenAI Whisper API
  • Self-hosted: No API key needed, fully offline
  • SenseVoice (234M): 50+ languages, emotion detection, audio event detection
  • Paraformer: 170x realtime on GPU
  • 16K+ GitHub stars, actively maintained

Integration approach

Since FunASR serves an OpenAI-compatible endpoint, LiteLLM could route STT requests to it like any OpenAI-compatible provider:

# User configuration
litellm.transcription(
    model="funasr/sensevoice-small",
    file=audio_file,
    api_base="http://localhost:8000"
)

Server setup

pip install funasr vllm fastapi uvicorn python-multipart
funasr-server --device cuda --port 8000
# POST /v1/audio/transcriptions ready

References

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

litellm - 💡(How to fix) Fix Feature request: Add FunASR as STT provider (OpenAI-compatible)