clipwright-silence

MCP tool for silence detection and OTIO timeline generation. Detects silent intervals in a media file and writes a KEEP-interval timeline (.otio) that clipwright-render can use for automated cut editing.

Overview

Input: Media file (video or audio), output OTIO path, optional detection parameters
Process: Runs the ffmpeg silencedetect filter (default) or Silero VAD (opt-in) to find silence intervals, inverts them to KEEP intervals, applies padding and merging, and writes an OTIO timeline
Output: New OTIO file with KEEP intervals; input media is never modified (non-destructive, readOnly)

MCP Tool

clipwright_detect_silence

Parameters

Name	Type	Default	Description
`media`	`string`	required	Input media file path (video or audio)
`output`	`string`	required	Output OTIO timeline file path (`.otio` extension)
`options`	`object`	`null`	DetectSilenceOptions (see below)

DetectSilenceOptions

Field	Type	Default	Description
`silence_threshold_db`	`float`	`-30.0`	Volume threshold (dB) for silence detection (`silencedetect` backend only; must be ≤ 0)
`min_silence_duration`	`float`	`0.5`	Minimum duration (seconds) to classify as silence (`silencedetect` backend only; must be > 0)
`padding`	`float`	`0.1`	Padding (seconds) added to both sides of each KEEP interval. Overlapping intervals are merged
`min_keep_duration`	`float`	`0.0`	KEEP intervals shorter than this value (seconds) are discarded after padding and merging
`backend`	`string`	`"silencedetect"`	Detection backend: `"silencedetect"` (ffmpeg) or `"vad"` (Silero VAD / ONNX)
`vad_threshold`	`float`	`0.5`	VAD backend only. Speech probability threshold (0.0–1.0); values ≥ this are speech
`vad_min_speech_duration`	`float`	`0.25`	VAD backend only. Minimum speech segment duration (seconds)
`vad_min_silence_duration`	`float`	`0.1`	VAD backend only. Minimum silence gap (seconds) between speech intervals

Dependencies

Package	Purpose
`clipwright`	Shared types, envelope, errors, subprocess runner
`mcp[cli]`	MCP server
`pydantic`	Parameter validation
`onnxruntime`	Silero VAD inference (VAD backend)

Installation and Startup

uv add clipwright-silence
clipwright-silence

Or within a uv workspace:

uv run --package clipwright-silence clipwright-silence

Prerequisites

Python 3.11 or later
ffmpeg and ffprobe available on PATH, or set via environment variables:
- CLIPWRIGHT_FFMPEG — path to the ffmpeg binary
- CLIPWRIGHT_FFPROBE — path to the ffprobe binary
For the vad backend: onnxruntime is bundled as a dependency; no additional binary is required

Metadata

Release files for clipwright-silence 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for clipwright-silence 0.4.0
File	Size	Uploaded
clipwright_silence-0.4.0.tar.gz	14.9 kB	Jul 15, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for clipwright-silence 0.4.0
File	Interpreter	ABI	Platform	Reset
clipwright_silence-0.4.0-py3-none-any.whl 17.9 kB Jul 15, 2026	Python 3	none	any	Details

Total release size: 32.7 kB

Release files / clipwright_silence-0.4.0.tar.gz

Download URL	clipwright_silence-0.4.0.tar.gz
Size	14.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`7cfb42315c7f8dab3105c74e7019d9876f8f85a9fc1bcb1a65e30c531c715853`
BLAKE2b-256 checksum How to use checksums	`4ad4a32167d27cc82a5dc3796d5cb77f5b4bc9d41bdb4a46896e8eb3ed4943a6`
Upload date	Jul 15, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/satoh-y-0323/clipwright
Publishing commit: github.com/satoh-y-0323/clipwright/tree/7b5cce6556a6126677e0cdebe6c7dbdb8cad1a55

Workflow

Publishing configuration: github.com/satoh-y-0323/clipwright/blob/7b5cce6556a6126677e0cdebe6c7dbdb8cad1a55/.github/workflows/publish.yml
Publishing logs: github.com/satoh-y-0323/clipwright/actions/runs/29428901356/attempts/1

Artifact

Subject: clipwright_silence-0.4.0.tar.gz
SHA-256 checksum: 7cfb42315c7f8dab3105c74e7019d9876f8f85a9fc1bcb1a65e30c531c715853 Verifying attestations

Release files / clipwright_silence-0.4.0-py3-none-any.whl

Download URL	clipwright_silence-0.4.0-py3-none-any.whl
Size	17.9 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`327b629c294badae05f9e8c6c2d954cc854f1ee030b56e99612293f899dc431e`
BLAKE2b-256 checksum How to use checksums	`01add9e89f8a4c7543ac1d2b13a5b73990d6f83ee6c17f3f18178f21330b101e`
Upload date	Jul 15, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/satoh-y-0323/clipwright
Publishing commit: github.com/satoh-y-0323/clipwright/tree/7b5cce6556a6126677e0cdebe6c7dbdb8cad1a55

Workflow

Publishing configuration: github.com/satoh-y-0323/clipwright/blob/7b5cce6556a6126677e0cdebe6c7dbdb8cad1a55/.github/workflows/publish.yml
Publishing logs: github.com/satoh-y-0323/clipwright/actions/runs/29428901356/attempts/1

Artifact

Subject: clipwright_silence-0.4.0-py3-none-any.whl
SHA-256 checksum: 327b629c294badae05f9e8c6c2d954cc854f1ee030b56e99612293f899dc431e Verifying attestations