ACE-Step Transcriber

by tukrooco.huggingface.tukroo/acestep-transcriber-demo

How the score works

  • Remote endpoint
  • 2 tools

Tools

  • acestep_transcriber_demo__lambda_
  • acestep_transcriber_demo_transcribe Transcribe speech or singing voice into structured Markdown. Uses ACE-Step/acestep-transcriber (Qwen2.5-Omni architecture, 11B) to produce a transcript with a `# Languages` line and `# Lyrics` section annotated with song-structure tags ([Intro], [Verse 1], [Chorus]...). Works for speech in 50+ languages and for singing voice. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: The structured transcript as Markdown text.

As the server's own listing gives them. We never call a tool.