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.
Python agent-skillsai-agentsaudio-processingcaptionsclaude-codecodexcoding-agentcursorffmpegloudness-normalizationmcpmcp-servermodel-context-protocolpythonsubtitlestranscodingvideovideo-editingvideo-processingwhisper
chore(release): bump version to 2.7.0 [skip ci]
github-actions[bot]cb10cfbc5373
diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.jsonindex 9b33b02..49bab3f 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, capability detection, probe-first / verify-last workflow. No cloud, no API keys.",- "version": "2.6.0",+ "version": "2.7.0","author": {"name": "kajisho5","url": "https://github.com/kajisho5"diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 2a23f93..bb13f31 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -4,12 +4,19 @@## Unreleased+(nothing yet)++## 2.7.0++_Automated release: version and notes generated from pull requests merged since 2.6.0._+- feat: Parakeet speech engines, built by [@rymalia](https://github.com/rymalia) in #305. `parakeet-mlx` and `parakeet.cpp` (`parakeet-cli` + a `.gguf`) for `caption.py --transcribe` and `silence.py --filler --transcribe`; `--engine` / `FFMPEG_SKILL_ASR_ENGINE` pick one, and a named engine runs as asked. `auto` runs Parakeet for English speech (an English `--language`, else whisper.cpp's language detector) and Whisper otherwise. Speech whose language nobody named and nothing here could detect goes to a Whisper engine that can run; Parakeet runs on English assumed only when there is none or every one failed, and the result's top-level `notes` then says the transcript is wrong if the speech is not English (new for `silence.py`). Results carry `transcription` (engine, model, language, routing) in every caption `--mode`; `silence.py`'s `filler.source` is `parakeet:ENGINE` for them. A Parakeet engine whose output is not a readable transcript is a failed run and the next engine is tried; its own empty answer is the `no_speech` refusal. `transcribe_result()` / `transcribe_words_result()` return what a call used as a `Transcription`, and `transcribe()` / `transcribe_words()` keep their return shapes. New optional contract capability `external:parakeet`.- fix: whisper.cpp is told to detect the language (`-l auto`) when `--language` / `--filler-lang` is not given. It was given no `-l`, and its own default is English, so `caption.py --transcribe` and `silence.py --filler --transcribe` decoded speech in any other language as English. The result's `transcription.language` stays `null` for a language the engine identified itself.- fix: the "no local speech-to-text engine found" refusal, with its install lines, now only means no engine was found. A whisper.cpp that was installed but failed, with nothing after it, got that refusal; now the refusal names each engine that was found and why it did not transcribe (`kind: input`, `reason: "engine_failed"` or `"english_only"`, `engines[].detail` with the engine's own error line).- fix: a faster-whisper that raises while loading or running its model (an offline first run, a broken install) is a failed engine: `caption.py --transcribe` logs "faster-whisper found but failed" and tries the next engine instead of refusing with "faster-whisper found no speech", and `silence.py --filler --transcribe` can fall back to Parakeet. The exception used to be swallowed in the engine's thread. An engine that ran and found no segment is still the `no_speech` refusal.- docs: parakeet-mlx downloads its default model (`mlx-community/parakeet-tdt-0.6b-v2`) from Hugging Face on first use, as faster-whisper does, and openai-whisper downloads its model from OpenAI. The install hint, README, docs/contract.md and references/scripts.md now say so, and that the audio never leaves the machine (inference is local). The skill's own code opens no connection, but faster-whisper runs inside the skill's process, so its first-run download is made from that process. The refusal's "all run offline" is gone: a first run that downloads is not offline.- feat(contract): `execution.model_downloads` says which speech engine fetches its model on first use, from where, and in which process (faster-whisper in the skill's own; parakeet-mlx and openai-whisper in their own child processes; whisper.cpp and parakeet.cpp never). `execution.network: false` keeps its meaning, the skill's own code, and no longer reads as a promise that a first `--transcribe` is network-free.+- feat: Parakeet speech engines for --transcribe (#312)## 2.6.0diff --git a/docs/contract.md b/docs/contract.mdindex d4f3e61..ee9d9c8 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 (`2.6.0`) | any release |+| `skill.version` | the npm / package.json version (`2.7.0`) | any release |A release that adds a tool or a flag keeps `contract_version`; a breaking change to theToolSpec 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": "2.6.0", "execution_mode": "local", "kind": "execution",+ "skill": {"id": "ffmpeg-skill", "version": "2.7.0", "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.mdindex 67c2aac..5a3afba 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 **2.6.0** (notes in CHANGELOG.md); **2.2.1** — `render.py`, `caption.py --mode mux` and+The released version today is **2.7.0** (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: everymissing 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 aneditor as FCPXML, CMX 3600 EDL or OpenTimelineIO (clips, speed, dissolves, music bed, chapterdiff --git a/package.json b/package.jsonindex 899dc43..03a7f24 100644--- a/package.json+++ b/package.json@@ -1,6 +1,6 @@{"name": "ffmpeg-skill",- "version": "2.6.0",+ "version": "2.7.0","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",