Skip to content

Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

chore(release): bump version to 2.9.0 [skip ci]

github-actions[bot]86e7da538303
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
index ac1b738..f8a731d 100644
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
{
"name": "ffmpeg-skill",
"description": "Local FFmpeg video/audio editing for coding agents: 42 tools with a machine-readable contract and MCP server, capability detection, probe-first / verify-last workflow. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.",
- "version": "2.8.7",
+ "version": "2.9.0",
"author": {
"name": "kajisho5",
"url": "https://github.com/kajisho5"
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 812a0d5..6ed7300 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,9 +4,16 @@
## Unreleased
+(nothing yet)
+
+## 2.9.0
+
+_Automated release: version and notes generated from pull requests merged since 2.8.7._
+
### Added
- **A per-machine speech model, and `--model` on `silence.py --filler --transcribe` (#328).** `FFMPEG_SKILL_ASR_MODEL` is the model `caption.py --transcribe` and `silence.py --filler --transcribe` use when no `--model` is given (else `base`, as before), so a machine with `ggml-large-v3-turbo.bin` no longer needs `--model` on every call, and filler timing is no longer stuck on `base`. An explicit `--model` still wins and still goes to whichever engine runs. A Parakeet model in the variable (an `mlx-community/parakeet-*` repo or a `.gguf`) is offered to the Parakeet engines only and the Whisper engines keep `base`, so a machine default never makes auto's Whisper route for another language fail on a model it cannot load; a Whisper name leaves Parakeet routing and Parakeet's own model as they were. The result's `transcription.model` names the model that ran. `caption.py --model` no longer advertises a `base` default in its schema (it is resolved at run time); `silence.py`'s MCP schema gains `model`.
+- feat: per-machine ASR model (FFMPEG_SKILL_ASR_MODEL) and silence.py --model (#330)
## 2.8.7
diff --git a/docs/contract.md b/docs/contract.md
index ed19711..9d68f8c 100644
--- a/docs/contract.md
+++ b/docs/contract.md
@@ -21,7 +21,7 @@ The contract is derived from the code that runs, not maintained beside it:
| Field | Meaning | Changes when |
|---|---|---|
| `contract_version` | shape of this document (`1.0`) | a key is renamed, removed or changes meaning |
-| `skill.version` | the npm / package.json version (`2.8.7`) | any release |
+| `skill.version` | the npm / package.json version (`2.9.0`) | any release |
A release that adds a tool or a flag keeps `contract_version`; a breaking change to the
ToolSpec shape bumps it. Consumers pin on `contract_version` and read `skill.version`
@@ -119,7 +119,7 @@ JSON would have been rewritten for that. The flat keys, typed per tool in `outpu
"contract_version": "1.0",
"deprecated": [],
"removed": [{"what": "...", "since": "1.10.0", "replacement": "...", "removed_in": "2.0.0", "where": "cli | json | mcp | behaviour"}],
- "skill": {"id": "ffmpeg-skill", "version": "2.8.7", "execution_mode": "local", "kind": "execution",
+ "skill": {"id": "ffmpeg-skill", "version": "2.9.0", "execution_mode": "local", "kind": "execution",
"entrypoints": {"cli": "...", "mcp": "...", "contract": "...", "doctor": "..."},
"not_provided": ["AI reasoning", "decisions", "production plans", "project IR", "approvals", "network access", "transcription engine"]},
"requirements": {"python": ">=3.9 (standard library only)", "ffmpeg": ">=5.0", "ffprobe": ">=5.0"},
diff --git a/docs/roadmap.md b/docs/roadmap.md
index 19024c0..a40a683 100644
--- a/docs/roadmap.md
+++ b/docs/roadmap.md
@@ -17,7 +17,7 @@ minor and `fix` PRs into a patch, so each block below is one or two `feat` PRs p
- **planned** — not released. Nothing below a *planned* heading exists in any published version;
the feature lines are the intent, not a description of the code.
-The released version today is **2.8.7** (notes in CHANGELOG.md); **2.2.1** — `render.py`, `caption.py --mode mux` and
+The released version today is **2.9.0** (notes in CHANGELOG.md); **2.2.1** — `render.py`, `caption.py --mode mux` and
`sequence.py` now check every input before any work, as `join.py --list` (2.2.0) does: every
missing or broken TTS/render segment is named at once (`--on-missing skip` joins the rest). 2.1.0: `render.py --export-timeline` hands the cut to an
editor as FCPXML, CMX 3600 EDL or OpenTimelineIO (clips, speed, dissolves, music bed, chapter
diff --git a/package.json b/package.json
index fc65783..8e80595 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
{
"name": "ffmpeg-skill",
- "version": "2.8.7",
+ "version": "2.9.0",
"description": "Agent Skill that gives coding agents (Claude Code, Cursor, Codex) a local video editor: 42 FFmpeg tools with a machine-readable contract, contract-derived MCP server, FFmpeg capability detection, probe-first / verify-last workflow. Cut, join, silence removal, fit, captions and karaoke, overlays, motion graphics, HDR to SDR, LUTs, audio clean-up and typed dynamics, sync with drift correction, multicam, loudness, delivery checks, project rendering, batch. No API keys, no cloud, no dependencies.",
"keywords": [
"ffmpeg",