extract_audio_from_video
Extract audio track from video file
How to use it
Project documentation lists extract_audio_from_video for the MCP Ffmpeg MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install MCP Ffmpeg
uv --directory /path/to/mcp-ffmpeg run python main.pyOther tools in MCP Ffmpeg (26)
Insert B-roll clips as overlays at specific timestamps
Add fade-in / fade-out effects
Add image watermarks/logos with position & opacity
Burn SRT subtitles with customizable font styling
Add timed text overlays with full styling control
Change aspect ratio with pad or crop mode
Speed up or slow down playback (0.25x to 4x+)
Join multiple videos with optional xfade transitions
Convert between audio formats (mp3, wav, aac)
Batch convert format, bitrate, sample rate, channels
Convert between formats (mp4, mov, avi, etc.)
Batch convert format, resolution, codecs, bitrate, frame rate
Verify server is running and responsive
Detect and remove silent segments automatically
Set audio bitrate (128k, 192k, 320k)
Set mono (1) or stereo (2)
Set sample rate (44100, 48000 Hz)
Set audio bitrate within video
Set audio channels within video
Change audio codec within video (aac, mp3)
Set audio sample rate within video
Set video bitrate (e.g., 2500k, 5M)
Change video codec (libx264, libx265, vp9)
Adjust frame rate (24, 30, 60 fps)
Scale to target resolution (e.g., 1920x1080)
Trim video to specific start/end times