Feature Request: Add FunASR Speech-to-Text component

[LauraGPT]

Feature Request

Langflow is an excellent visual AI workflow builder. A Speech-to-Text component powered by FunASR would enable audio processing workflows.

Use cases:

• Voice input → STT → LLM processing → TTS output
• Audio file transcription → text processing pipeline
• Meeting recording → transcription → summarization

Why FunASR?

• OpenAI-compatible API: funasr-server provides /v1/audio/transcriptions endpoint
• SenseVoice: Ultra-fast ASR (234M params), 50+ languages
• Complete pipeline: VAD + ASR + punctuation + speaker diarization in one call
• Self-hosted: Fully local, no API key needed

Quick start:

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

• GitHub: https://github.com/modelscope/FunASR (16K+ stars)
• SenseVoice: https://github.com/FunAudioLLM/SenseVoice (8K+ stars)