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 #5728] Feature: Add FunASR as a self-hosted audio transcription / STT provider #5262

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/5728

Feature Request

AnythingLLM currently supports the built-in model and OpenAI for audio transcription. Adding FunASR as a self-hosted option would give users a powerful, privacy-friendly alternative.

Why FunASR?

  • OpenAI-compatible API: FunASR provides /v1/audio/transcriptions endpoint — same API format as OpenAI Whisper, so integration could leverage the existing OpenAI transcription path
  • Self-hosted: Fully local, no API keys needed. Ideal for privacy-sensitive deployments
  • 50+ languages with SenseVoice model (234M params, non-autoregressive, very fast)
  • Rich features: Built-in VAD, punctuation, speaker diarization, emotion detection
  • 16K+ GitHub stars, 1M+ monthly pip installs

Quick setup

pip install funasr vllm
funasr-server --device cuda
# Server runs at localhost:8000 with OpenAI-compatible API

Since FunASR exposes an OpenAI-compatible /v1/audio/transcriptions endpoint, the simplest integration path might be allowing users to point the existing OpenAI transcription provider at a custom base URL (like http://localhost:8000), similar to how LLM providers can point to local endpoints.

References:

Originally created by @LauraGPT on GitHub (May 30, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5728 ## Feature Request AnythingLLM currently supports the built-in model and OpenAI for audio transcription. Adding **FunASR** as a self-hosted option would give users a powerful, privacy-friendly alternative. ## Why FunASR? - **OpenAI-compatible API**: FunASR provides `/v1/audio/transcriptions` endpoint — same API format as OpenAI Whisper, so integration could leverage the existing OpenAI transcription path - **Self-hosted**: Fully local, no API keys needed. Ideal for privacy-sensitive deployments - **50+ languages** with SenseVoice model (234M params, non-autoregressive, very fast) - **Rich features**: Built-in VAD, punctuation, speaker diarization, emotion detection - **16K+ GitHub stars**, 1M+ monthly pip installs ## Quick setup ```bash pip install funasr vllm funasr-server --device cuda # Server runs at localhost:8000 with OpenAI-compatible API ``` Since FunASR exposes an OpenAI-compatible `/v1/audio/transcriptions` endpoint, the simplest integration path might be allowing users to point the existing OpenAI transcription provider at a custom base URL (like `http://localhost:8000`), similar to how LLM providers can point to local endpoints. **References:** - FunASR: https://github.com/modelscope/FunASR - SenseVoice: https://github.com/FunAudioLLM/SenseVoice
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
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#5262
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?