@writepanda/mcp 1.229.0 → 1.234.0

package/bin/server.mjs

@@ -819,7 +819,7 @@ const TOOLS = [
 	{
 		name: "system_get_transcription_language",
 		description:
-			"Workspace transcription language. auto = Parakeet TDT v3, which detects the language itself across 25 languages, English included: Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Ukrainian. Anything else names a Whisper language.",
+			"Workspace transcription language + on-device engine, and the engine a run would use and why: { language, engine (auto|parakeet|whisper), route { engine, lockedLanguage, reason }, whisperModel { downloaded, size } }. auto language = Parakeet TDT v3 detects it (25 languages: Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Ukrainian). With engine auto, English stays on Parakeet (keeps fillers) and any other named language is transcribed by Whisper LOCKED to it (no drift into English).",
 		inputSchema: { type: "object", properties: {} },
 		command: "system.get-transcription-language",
 	},
@@ -846,7 +846,7 @@ const TOOLS = [
 	{
 		name: "system_set_transcription_language",
 		description:
-			"Set the workspace transcription language. auto = Parakeet TDT v3, which detects the language itself across 25 languages, English included: Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Ukrainian. For any of those (e.g. Romanian) use auto; their names are accepted and saved as auto. The other values use Whisper, a ~1.1 GB download: tell the user first (system.is-whisper-model-downloaded via pandastudio_call).",
+			"Set the workspace transcription language. auto = Parakeet TDT v3 detects it. english/en is saved as auto (Parakeet keeps filler words). Any other language (french, romanian, chinese ...) is saved as itself and, with engine auto, transcribed by Whisper large-v3-turbo LOCKED to it (task transcribe, never translate): Parakeet can't be locked and drifts into English on accented speech. Whisper is a one-time ~550 MB download: if system_get_transcription_language whisperModel.downloaded is false, ask the user, then system_download_whisper_model. Keep a European language on Parakeet with system_set_transcription_preferences engine parakeet.",
 		inputSchema: {
 			type: "object",
 			properties: {
@@ -1635,7 +1635,7 @@ const TOOLS = [
 	{
 		name: "project_new",
 		description:
-			"Create a project; withMedia imports videos as clips, or AUDIO files (MP3 / WAV / M4A / AAC / FLAC / OGG) as an audio-only podcast project. speakers = one audio file per speaker (host first): a multi-speaker audio clip synced by audio.",
+			"Create a project; withMedia imports videos as clips (each whole, or only a {path, sourceStartMs, sourceEndMs} range), or AUDIO files (MP3 / WAV / M4A / AAC / FLAC / OGG) as an audio-only podcast project. speakers = one audio file per speaker (host first): a multi-speaker audio clip synced by audio. Returns editedDurationMs and warnings (e.g. the same footage repeated on several clips, or longer than parentProjectId's project): read them before going on.",
 		inputSchema: {
 			type: "object",
 			properties: {
@@ -1645,8 +1645,23 @@ const TOOLS = [
 				name: { type: "string" },
 				withMedia: {
 					type: "array",
-					items: { type: "string" },
-					description: "Videos, or audio files (an audio-only project). Not both.",
+					items: {
+						anyOf: [
+							{ type: "string" },
+							{
+								type: "object",
+								properties: {
+									path: { type: "string" },
+									sourceStartMs: { type: "number" },
+									sourceEndMs: { type: "number" },
+								},
+								required: ["path"],
+								additionalProperties: false,
+							},
+						],
+					},
+					description:
+						"Videos, or audio files (an audio-only project). Not both. An item is a path (whole file) or {path, sourceStartMs, sourceEndMs} for only that range (ms in the file's own time): excerpts / previews, the same file may repeat with different ranges.",
 				},
 				speakers: {
 					type: "array",
@@ -1699,7 +1714,7 @@ const TOOLS = [
 	{
 		name: "project_add_clip",
 		description:
-			"Append or insert a video clip, an audio file (audio-only projects only), or a still image shown for durationMs, on the main track (later content moves with it). atMs (edited time) inserts at that moment, splitting the clip under it; add replaceToMs to replace [atMs, replaceToMs) with the clip (e.g. a re-recorded take).",
+			"Append or insert a video clip (whole, or only sourceStartMs-sourceEndMs of it), an audio file (audio-only projects only), or a still image shown for durationMs, on the main track (later content moves with it). atMs (edited time) inserts at that moment, splitting the clip under it; add replaceToMs to replace [atMs, replaceToMs) with the clip (e.g. a re-recorded take).",
 		inputSchema: {
 			type: "object",
 			properties: {
@@ -1719,12 +1734,39 @@ const TOOLS = [
 					description:
 						"With atMs: replace [atMs, replaceToMs), merge overlapping or adjacent cuts, and remove fully trimmed clips.",
 				},
+				sourceStartMs: {
+					type: "number",
+					description:
+						"Video / audio: in-point, ms in the file's own time. Add only an excerpt instead of the whole file.",
+				},
+				sourceEndMs: {
+					type: "number",
+					description: "Video / audio: out-point, ms in the file's own time (default: its end).",
+				},
 				expectedRevision: { type: "number" },
 			},
 			required: ["media"],
 		},
 		command: "project.add-clip",
 	},
+	{
+		name: "project_set_clip_range",
+		description:
+			"Set which part of a clip's media plays (in / out point, ms in the clip's own source time), like dragging its edges: head + tail cut, old edge cuts replaced, inner cuts kept. Turns a full-length clip into an excerpt. Returns editedDurationMs + warnings.",
+		inputSchema: {
+			type: "object",
+			properties: {
+				id: { type: "string" },
+				path: { type: "string" },
+				clipId: { type: "string" },
+				sourceStartMs: { type: "number", description: "Default 0." },
+				sourceEndMs: { type: "number", description: "Default: the media's end." },
+				expectedRevision: { type: "number" },
+			},
+			required: ["clipId"],
+		},
+		command: "project.set-clip-range",
+	},
 	{
 		name: "project_set_clip_duration",
 		description: "Change how long an image clip shows (later content moves).",
@@ -3332,7 +3374,7 @@ const TOOLS = [
 	{
 		name: "project_save",
 		description:
-			"Overwrite a project file with `project` (pass expectedRevision). Without it, returns the current revision. Verbs already autosave.",
+			"Overwrite a project file with `project` (pass expectedRevision). Without it, returns the current revision. Verbs already autosave. Clips have no in/out or speed fields (sourceStartMs, inMs, speed, ...): those are rejected, use project_set_clip_range / project_add_speed.",
 		inputSchema: {
 			type: "object",
 			properties: {
@@ -4345,13 +4387,13 @@ const TOOLS = [
 	{
 		name: "system_set_transcription_preferences",
 		description:
-			"Save workspace language and provider atomically. Confirm consent to upload audio for cloud. Cloud and apple cannot use auto.",
+			"Save workspace transcription language, provider and/or on-device engine atomically (pass any). engine: auto (Parakeet for English/auto-detect, Whisper LOCKED to any other named language), parakeet (keeps fillers, detects the language, can't be locked), whisper (locks to the language). Confirm consent to upload audio for cloud. Cloud and apple cannot use auto.",
 		inputSchema: {
 			type: "object",
-			required: ["language", "provider"],
 			properties: {
 				language: { type: "string" },
 				provider: { type: "string", enum: ["local", "apple", "deepgram", "elevenlabs"] },
+				engine: { type: "string", enum: ["auto", "parakeet", "whisper"] },
 			},
 		},
 		command: "system.set-transcription-preferences",
@@ -4360,7 +4402,7 @@ const TOOLS = [
 	{
 		name: "transcript_transcribe",
 		description:
-			"Transcribe clips with word timestamps (default: only clips without words). To REDO a transcript (wrong language, bad run) confirm language, pass per-run language and provider overrides, then force: true (all clips) or clipId. Word fixes are re-applied; tell the user about result droppedWordEdits[] (fixes that may need redoing). Each clip is transcribed only over the part it plays (head trim to out-point, e.g. one half of a split; result transcribedRanges[]). ASYNC: { jobId }, job_wait. Concurrent saves are merged and retried (three attempts). Exhausted conflicts report code revision_conflict / status 409 (job.errorDetails for async jobs).",
+			"Transcribe clips with word timestamps (default: only clips without words). Engine: language auto/english = Parakeet; any other named language = local Whisper LOCKED to it (engine override). Returns { jobId, plan } (plan = engine + reason, ranges, totalAudioMs: the audio that will be processed; tell the user for long jobs). To REDO a transcript (wrong language, bad run) confirm language, pass per-run language and provider overrides, then force: true (all clips) or clipId. Word fixes are re-applied; tell the user about result droppedWordEdits[] (fixes that may need redoing). Each clip is transcribed only over the part it plays (head trim to tail trim, e.g. one half of a split; only the kept parts when cuts hide most of a long recording; result transcribedRanges[]). ASYNC: { jobId }, job_wait. Concurrent saves are merged and retried (three attempts). Exhausted conflicts report code revision_conflict / status 409 (job.errorDetails for async jobs).",
 		inputSchema: {
 			type: "object",
 			properties: {
@@ -4379,10 +4421,54 @@ const TOOLS = [
 						"Per-run provider. apple stays on this Mac. Audio is sent to the selected cloud provider.",
 				},
 				force: { type: "boolean", description: "Re-transcribe clips that already have words." },
+				engine: {
+					type: "string",
+					enum: ["auto", "parakeet", "whisper"],
+					description:
+						"Per-run on-device engine (provider local). auto: Parakeet for English/auto, Whisper LOCKED to any other named language. parakeet keeps fillers but can't be locked to a language.",
+				},
+				dryRun: {
+					type: "boolean",
+					description:
+						"Return the plan (engine + reason, per-clip source ranges, totalAudioMs) without transcribing. Use before long jobs.",
+				},
 			},
 		},
 		command: "transcript.transcribe",
 	},
+	{
+		name: "system_download_whisper_model",
+		description:
+			"Download the Whisper large-v3-turbo model (~550 MB, once; then offline). Needed when a run routes to Whisper (any named language except English with engine auto, or engine whisper). ASK the user first. ASYNC: { jobId }, job_wait.",
+		inputSchema: { type: "object", properties: {} },
+		command: "system.download-whisper-model",
+	},
+	{
+		name: "transcript_import",
+		description:
+			"Replace a clip's transcript from a file: SRT, VTT (inline <00:00:01.500> word times supported), or word-timed JSON (whisper / faster-whisper / whisperX segments[].words[], {words:[...]}, {word_segments:[...]}, or [{word|text,start,end}] in seconds; startMs/endMs in ms). timeBase REQUIRED: source (media file time) or edited (the cut video's timeline; mapped through cuts/speed). Errors (lines going backwards, ending before starting, outside the clip) refuse with line numbers; overlaps are trimmed with a warning. Line-level timing is ALIGNED to measured word timings (align auto: the clip's current words, else a local transcription of just those lines = async { jobId }); without any, words are spread per line and alignment.method is 'proportional' (tell the user). Cuts kept; word fixes re-applied (droppedWordEdits[] otherwise); same word at same moment keeps its id. dryRun previews.",
+		inputSchema: {
+			type: "object",
+			properties: {
+				id: { type: "string" },
+				path: { type: "string" },
+				clipId: {
+					type: "string",
+					description: "Optional when the project has one clip with audio.",
+				},
+				file: { type: "string", description: "Absolute path to the .srt/.vtt/.json file." },
+				content: { type: "string", description: "The file's text instead of file." },
+				format: { type: "string", enum: ["auto", "srt", "vtt", "json"] },
+				timeBase: { type: "string", enum: ["source", "edited"] },
+				align: { type: "string", enum: ["auto", "existing", "transcribe", "proportional"] },
+				language: { type: "string" },
+				dryRun: { type: "boolean" },
+				expectedRevision: { type: "number" },
+			},
+			required: ["timeBase"],
+		},
+		command: "transcript.import",
+	},
 	{
 		name: "transcript_get",
 		description:
@@ -4755,6 +4841,39 @@ const TOOLS = [
 		command: "caption.set-template",
 	},
 
+	{
+		name: "caption_set_punctuation",
+		description:
+			'Clean punctuation out of the CAPTIONS in one call (same as Captions > Clean up punctuation, one undo step). preset clean (default): removes full stops, commas, ! : ; … quotes dashes brackets, KEEPS question marks (keepQuestionMarks false removes them); all; none (show the transcript\'s punctuation). Or remove: [period, comma, question, exclamation, colon, ellipsis, quotes, dashes, brackets]. The transcript text is NOT changed (timings, cuts, sentence breaks intact; reversible). Never merges words ("Bonjour.Merci" -> "Bonjour Merci"); keeps j\'ai, aujourd\'hui, peut-être, 3.5, 10:30, writepanda.ai.',
+		inputSchema: {
+			type: "object",
+			properties: {
+				id: { type: "string" },
+				path: { type: "string" },
+				preset: { type: "string", enum: ["clean", "all", "none"] },
+				remove: {
+					type: "array",
+					items: {
+						type: "string",
+						enum: [
+							"period",
+							"comma",
+							"question",
+							"exclamation",
+							"colon",
+							"ellipsis",
+							"quotes",
+							"dashes",
+							"brackets",
+						],
+					},
+				},
+				keepQuestionMarks: { type: "boolean" },
+				expectedRevision: { type: "number" },
+			},
+		},
+		command: "caption.set-punctuation",
+	},
 	{
 		name: "caption_set_style",
 		description:
@@ -4934,6 +5053,48 @@ const TOOLS = [
 		},
 		command: "media.generate-narration",
 	},
+	{
+		name: "media_regenerate_narration",
+		description:
+			"Regenerate a narration already on the timeline IN PLACE from its stored source (script, model, voice, tone on audioOverlays[].generatedFrom). Pass only what changes (text with the edited script, voice, model, ...). Same start, volume, fades, ducking; length = new audio. A transcribed narration is re-transcribed (transcribeJobId: job_wait it). One undo step. No stored source (older narration) = pass text.",
+		inputSchema: {
+			type: "object",
+			properties: {
+				id: { type: "string" },
+				path: { type: "string" },
+				regionId: { type: "string", description: "The narration's audio overlay id (audio-N)." },
+				text: { type: "string", description: "New script (default: stored)." },
+				model: { type: "string", description: "New engine; without voice uses its default voice." },
+				voice: { type: "string" },
+				style: { type: "string", description: "Tone (cloud); '' clears." },
+				language: { type: "string" },
+				speed: { type: "number" },
+				pronunciations: { type: "object", description: 'e.g. {"Kamal":"Ka mal"}' },
+				expectedRevision: { type: "number" },
+			},
+			required: ["regionId"],
+		},
+		command: "media.regenerate-narration",
+	},
+	{
+		name: "media_regenerate_image",
+		description:
+			"Regenerate a generated picture on the timeline (a B-roll beat's image) IN PLACE from its stored prompt (editor.mediaOverlayRegions[].generatedImage); pass prompt to change it. Timing, push, transitions, shutter kept. PAID on the user's image connector: only when they asked. One undo step.",
+		inputSchema: {
+			type: "object",
+			properties: {
+				id: { type: "string" },
+				path: { type: "string" },
+				regionId: { type: "string", description: "The picture's overlay id." },
+				prompt: { type: "string", description: "New prompt (default: stored)." },
+				aspectRatio: { type: "string" },
+				quality: { type: "string", enum: ["low", "medium", "high"] },
+				expectedRevision: { type: "number" },
+			},
+			required: ["regionId"],
+		},
+		command: "media.regenerate-image",
+	},
 	{
 		name: "recording_list_sources",
 		description: "List displays and windows for recording_start's source.",

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@writepanda/mcp",
-	"version": "1.229.0",
+	"version": "1.234.0",
 	"description": "Model Context Protocol server for PandaStudio. Exposes the desktop video editor's automation surface to Cursor, Continue, Cline, Claude Desktop, and any MCP-compliant client.",
 	"keywords": [
 		"pandastudio",