Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #5727] Feature Request: Add FunASR/SenseVoice as Audio Transcription provider #5261

New Issue
Closed
opened 2026-06-05 14:52:59 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 14:52:59 -04:00
Owner
Copy Link
Copy Source

Originally created by @LauraGPT on GitHub (May 30, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5727

Feature Request

AnythingLLM already supports audio transcription and STT — FunASR would be an excellent addition as a self-hosted, high-performance provider.

Why FunASR?

  • OpenAI-compatible API: FunASR provides /v1/audio/transcriptions endpoint — could work as a drop-in replacement
  • SenseVoice: Ultra-fast non-autoregressive ASR (234M params), 5-10x faster than Whisper, 50+ languages
  • Fully self-hosted: No API key needed, completely local/private
  • Built-in features: VAD (speech segmentation), punctuation restoration, speaker diarization — all in one pipeline
  • Fun-ASR-Nano: LLM-based ASR (800M params) with hotword customization and context-aware recognition
  • Emotion detection: SenseVoice identifies speech emotions — could enrich document metadata

Server setup:

pip install funasr vllm fastapi uvicorn python-multipart
funasr-server --device cuda
# OpenAI-compatible /v1/audio/transcriptions at localhost:8000

Or Python API:

from funasr import AutoModel
model = AutoModel(model="iic/SenseVoiceSmall")
result = model.generate(input="audio.wav")
Originally created by @LauraGPT on GitHub (May 30, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5727 ## Feature Request AnythingLLM already supports audio transcription and STT — FunASR would be an excellent addition as a self-hosted, high-performance provider. **Why FunASR?** - **OpenAI-compatible API**: FunASR provides `/v1/audio/transcriptions` endpoint — could work as a drop-in replacement - **SenseVoice**: Ultra-fast non-autoregressive ASR (234M params), 5-10x faster than Whisper, 50+ languages - **Fully self-hosted**: No API key needed, completely local/private - **Built-in features**: VAD (speech segmentation), punctuation restoration, speaker diarization — all in one pipeline - **Fun-ASR-Nano**: LLM-based ASR (800M params) with hotword customization and context-aware recognition - **Emotion detection**: SenseVoice identifies speech emotions — could enrich document metadata **Server setup:** ```bash pip install funasr vllm fastapi uvicorn python-multipart funasr-server --device cuda # OpenAI-compatible /v1/audio/transcriptions at localhost:8000 ``` **Or Python API:** ```python from funasr import AutoModel model = AutoModel(model="iic/SenseVoiceSmall") result = model.generate(input="audio.wav") ``` - GitHub: https://github.com/modelscope/FunASR (16K+ stars) - SenseVoice: https://github.com/FunAudioLLM/SenseVoice (8K+ stars)
yindo added the enhancementIntegration Requestfeature request labels 2026-06-05 14:52:59 -04:00
yindo closed this issue 2026-06-05 14:52:59 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label Integration Request enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#5261
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?