Fal Whisper

Fast, asynchronous Whisper transcription for audio and video files with SRT subtitle export.

Install
cmdop skills install agensi-fal-whisper

Fal Whisper is an agent skill that connects to fal.ai’s Fast Whisper model to transcribe audio and video files into structured text. It is implemented in Python and uses an asynchronous queue — submit, poll, retrieve — to handle transcription jobs, which makes it more stable than synchronous approaches when processing large files.

The skill accepts both local files and remote files hosted at public URLs. Local files are sent via base64 encoding; remote files are referenced by URL. Supported formats include MP3, MP4, M4A, WAV, and FLAC, among others.

Transcription results are stored locally in a dedicated directory (~/.fal-whisper/). Each job produces at minimum a plain .txt file containing the full transcript. Optionally, the skill generates a SubRip (.srt) subtitle file with precision timestamps, suitable for import into video editing applications such as Premiere Pro or DaVinci Resolve. Word-level timestamps are also available.

Because audio transcription is computationally intensive, offloading it to fal.ai’s hardware avoids the overhead of running inference locally. Structured output — including text chunks and segment timestamps — makes downstream processing straightforward for agents that need to search, index, or caption audio content.

This skill is not an MCP server and exposes no callable tools in the MCP sense; it is a Python-based skill for agent workflows that already integrate with the fal.ai platform.

Use cases

  • Transcribe a recorded meeting MP4 into a searchable .txt file
  • Generate .srt subtitle files for video content ready for editing
  • Submit large audio files for async transcription without timeout issues
  • Transcribe cloud-hosted podcast episodes by passing a public URL
  • Extract word-level timestamps from audio for caption alignment
  • Store transcripts locally for later retrieval by an agent workflow

When to use it

  • The agent workflow needs to transcribe audio or video files into text
  • Output must include SRT subtitle files with timestamps
  • Files are large enough that synchronous processing would time out
  • Source files are either local (MP3, WAV, FLAC, M4A, MP4) or available at a public URL
  • The workflow is Python-based and integrates with fal.ai

When not to use it

  • No fal.ai access or account is available, as the skill depends on fal.ai infrastructure
  • Real-time or streaming transcription is required; the skill uses an async queue model
  • The agent runtime does not support Python-based skills
  • Only MCP-protocol tool calls are supported; this skill exposes no MCP tools
  • Files are not in a supported format or cannot be reached via public URL or local path