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 #5730] Feature request: Add FunASR as self-hosted STT provider #5265

New Issue
Closed
opened 2026-06-05 14:53:00 -04:00 by yindo · 0 comments
yindo commented 2026-06-05 14:53:00 -04:00
Owner
Copy Link
Copy Source

Originally created by @LauraGPT on GitHub (May 31, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5730

Feature Request

Add FunASR as a self-hosted speech-to-text provider for AnythingLLM.

Why

AnythingLLM supports voice input via Whisper. FunASR offers a self-hosted, OpenAI-compatible alternative:

  • OpenAI-compatible API: funasr-server serves POST /v1/audio/transcriptions — drop-in for existing Whisper integration
  • Self-hosted: No API key needed, runs alongside AnythingLLM
  • SenseVoice (234M): 50+ languages, emotion detection, 25x realtime on CPU
  • Better CJK support: Significantly better Chinese/Japanese/Korean accuracy than Whisper
  • 16K+ GitHub stars, MIT license

Setup

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

Users could configure STT_PROVIDER=funasr with STT_BASE_URL=http://localhost:8000.

References

Originally created by @LauraGPT on GitHub (May 31, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5730 ## Feature Request Add FunASR as a self-hosted speech-to-text provider for AnythingLLM. ### Why AnythingLLM supports voice input via Whisper. FunASR offers a self-hosted, OpenAI-compatible alternative: - **OpenAI-compatible API**: `funasr-server` serves `POST /v1/audio/transcriptions` — drop-in for existing Whisper integration - **Self-hosted**: No API key needed, runs alongside AnythingLLM - **SenseVoice** (234M): 50+ languages, emotion detection, 25x realtime on CPU - **Better CJK support**: Significantly better Chinese/Japanese/Korean accuracy than Whisper - **16K+ GitHub stars**, MIT license ### Setup ```bash pip install funasr vllm fastapi uvicorn python-multipart funasr-server --device cuda --port 8000 # POST /v1/audio/transcriptions ready ``` Users could configure `STT_PROVIDER=funasr` with `STT_BASE_URL=http://localhost:8000`. ### References - [FunASR](https://github.com/modelscope/FunASR) - [SenseVoice](https://github.com/FunAudioLLM/SenseVoice)
yindo closed this issue 2026-06-05 14:53:00 -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#5265
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?