Feature Proposal: Add FunASR Speech-to-Text Action Step

Automatisch is a self-hosted workflow automation tool (Zapier alternative). Adding speech-to-text would enable audio processing in automated workflows. FunASR (17.8K+ stars, https://github.com/modelscope/FunASR) provides:

• SenseVoice: Ultra-fast multilingual ASR (50x faster than Whisper-large)
• Paraformer: Production-grade ASR with timestamps and punctuation
• OpenAI-compatible API: POST /v1/audio/transcriptions

Since both Automatisch and FunASR are self-hosted tools, they integrate naturally. FunASR could serve as an action step that:

1. Accepts audio input from a trigger (e.g., new audio file uploaded)
2. Transcribes via local FunASR server
3. Passes transcribed text to subsequent workflow steps

This enables self-hosted voice-to-text automation without cloud dependencies.

Would adding a FunASR action be useful?