ottoport 1.13.1 → 1.14.0

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ottoport",
   "description": "One API for every model. Call chat, image, video, speech and music models through the OttoPort gateway — as MCP tools, slash commands, or the bundled CLI.",
-  "version": "1.13.1",
+  "version": "1.14.0",
   "author": {
     "name": "LITBOX LLC",
     "email": "support@ottoport.ai"

package/README.md

@@ -30,6 +30,7 @@ ottoport video "<prompt>" [--model kling-3.0] [--duration 5] [--resolution 1080p
 ottoport webhook status|retry <job-id>   # delivery attempts / redeliver now
 ottoport speech "<text>"  [--model gpt-4o-mini-tts] [--voice alloy] [--out speech.mp3]
 ottoport music "<prompt>" [--model suno-v5] [--duration 15] [--out song.mp3]
+ottoport music --model mirelo-sfx-2.0 --video <url> [--duration 8]   # soundtrack for a video
 
 ottoport install <host>   # wire the MCP server into an agent
 ottoport mcp              # run the MCP server on stdio

package/cli/ottoport.mjs

@@ -10,6 +10,7 @@
 //   ottoport video  "prompt" [--model kling-3.0] [--duration 5] [--out clip.mp4]
 //   ottoport speech "text" [--model gpt-4o-mini-tts] [--voice alloy] [--out speech.mp3]
 //   ottoport music  "prompt" [--model suno-v5] [--duration 15] [--out song.mp3]
+//   ottoport music  --model mirelo-sfx-2.0 --video <url> [--duration 8]
 //   ottoport collections [list | create "name"]
 //   ottoport mcp
 //   ottoport install <codex|claude|hermes|cursor|windsurf|claude-desktop>
@@ -24,6 +25,9 @@ import { readFile, stat, writeFile } from "node:fs/promises";
 const BASE = "https://ottoport.ai";
 
 // ── arg parsing ──────────────────────────────────────────────────────
+// Switches that never take a value, so `--draft "a boat"` keeps its prompt.
+const BOOLEAN_FLAGS = new Set(["draft"]);
+
 function parseArgs(argv) {
   const positional = [];
   const flags = {};
@@ -33,7 +37,7 @@ function parseArgs(argv) {
       const key = a.slice(2);
       if (key.startsWith("no-")) {
         flags[key.slice(3)] = false;
-      } else if (i + 1 < argv.length && !argv[i + 1].startsWith("--")) {
+      } else if (!BOOLEAN_FLAGS.has(key) && i + 1 < argv.length && !argv[i + 1].startsWith("--")) {
         const value = argv[++i];
         // Repeats accumulate rather than overwrite, so `--ref a --ref b` keeps
         // both. Everything downstream reads the last value of a scalar flag,
@@ -297,10 +301,14 @@ async function cmdImage(prompt, flags) {
 
 async function cmdVideo(prompt, flags) {
   // A depth model needs only --video; the gateway refuses a prompt there.
-  if (!prompt && !last(flags.video)) die("video requires a prompt: ottoport video \"a drone shot\" (or --video <url> on a depth model)");
+  // A draft's 1080p render takes everything from the draft, the prompt included.
+  const draftId = last(flags["draft-id"]);
+  if (!prompt && !last(flags.video) && !draftId) die("video requires a prompt: ottoport video \"a drone shot\" (or --video <url> on a depth model)");
   const { baseUrl, apiKey } = config(flags);
+  // Drafts are Seedance 2.5's, so a draft with no model named is one of its.
+  const model = last(flags.model) || (flags.draft === true || draftId ? "seedance-2.5" : "kling-3.0");
   const body = {
-    model: last(flags.model) || "kling-3.0",
+    model,
     ...(prompt ? { prompt } : {}),
     ...(last(flags.video) ? { video_url: last(flags.video) } : {}),
     ...(last(flags.duration) ? { duration: Number(last(flags.duration)) } : {}),
@@ -312,6 +320,8 @@ async function cmdVideo(prompt, flags) {
     ...(references(flags) ? { reference_image_urls: references(flags) } : {}),
     ...(references(flags, "ref-video") ? { reference_video_urls: references(flags, "ref-video") } : {}),
     ...(references(flags, "ref-audio") ? { reference_audio_urls: references(flags, "ref-audio") } : {}),
+    ...(flags.draft === true ? { draft: true } : {}),
+    ...(draftId ? { draft_id: draftId } : {}),
     ...webhook(flags),
     ...collection(flags),
   };
@@ -338,6 +348,10 @@ async function cmdVideo(prompt, flags) {
   const url = job.data?.[0]?.url;
   if (url) {
     console.log(outputLine(job.data[0]));
+    // The draft's job id is what renders it in 1080p, so say it.
+    if (!draftId && (body.draft || model.endsWith("-draft"))) {
+      process.stderr.write(`draft ${job.id} — render it in 1080p within seven days: ottoport video --model ${model} --draft-id ${job.id}\n`);
+    }
     if (flags.out) await download(url, last(flags.out));
   } else {
     console.log(JSON.stringify(job, null, 2));
@@ -381,11 +395,14 @@ async function cmdWebhook(action, jobId, flags) {
 }
 
 async function cmdAudio(kind, prompt, flags) {
-  if (!prompt) die(`${kind} requires a prompt: ottoport ${kind} "hello"`);
+  // A sound-effects model scores a video, so the prompt is optional with one.
+  const video = kind === "music" ? last(flags.video) : undefined;
+  if (!prompt && !video) die(`${kind} requires a prompt: ottoport ${kind} "hello"`);
   const { baseUrl, apiKey } = config(flags);
   const body = {
     model: last(flags.model) || (kind === "speech" ? "gpt-4o-mini-tts" : "suno-v5"),
-    prompt,
+    ...(prompt ? { prompt } : {}),
+    ...(video ? { video_url: video } : {}),
     ...(last(flags.voice) ? { voice: last(flags.voice) } : {}),
     ...(last(flags.duration) ? { duration: Number(last(flags.duration)) } : {}),
     ...(last(flags.format) ? { format: last(flags.format) } : {}),
@@ -475,14 +492,20 @@ Usage:
                             [--aspect-ratio 16:9] [--seed 7] [--image <url>]
                             [--last-frame <url>] [--ref <url>[,<url>…]]
                             [--ref-video <url>[,<url>…]] [--ref-audio <url>[,<url>…]]
-                            [--webhook-url https://…] [--webhook-secret <s>]
+                            [--draft] [--webhook-url https://…] [--webhook-secret <s>]
                             [--no-wait] [--out clip.mp4]
+  ottoport video --draft-id <job-id> [--model seedance-2.5] [--out clip.mp4]
+                            render a Seedance 2.5 draft (--draft, or the
+                            seedance-2.5-draft model) in 1080p, within 7 days
   ottoport video --model video-depth-anything --video <url> [--out depth.mp4]
                             turn a video (≤60s) into a grayscale depth video
   ottoport webhook status <job-id> [--json]   delivery attempts and responses
   ottoport webhook retry  <job-id> [--json]   redeliver a finished job's webhook now
   ottoport speech "<text>" [--model gpt-4o-mini-tts] [--voice alloy] [--format mp3] [--out speech.mp3]
   ottoport music  "<prompt>" [--model suno-v5] [--duration 15] [--format mp3] [--out song.mp3]
+  ottoport music  ["<prompt>"] --model mirelo-sfx-2.0 --video <url> [--duration 8] [--out sfx.wav]
+                            a soundtrack synced to the video, dialogue kept;
+                            set --duration to the clip's length (it bills)
   ottoport collections [list] [--json]          collections in the key's project
   ottoport collections create "<name>" [--description "..."] [--external-id <id>]
   ottoport mcp
@@ -512,6 +535,8 @@ Examples:
   ottoport image --model seedream-5.0-layers --image https://…/poster.png
   ottoport speech "Welcome to OttoPort" --voice alloy --out welcome.mp3
   ottoport music "lo-fi focus beat" --duration 20 --out focus.mp3
+  ottoport music "rain on a tin roof" --model mirelo-sfx-2.0 --duration 10 --format mp3 --out rain.mp3
+  ottoport music --model mirelo-sfx-2.0 --video https://example.com/chase.mp4 --duration 8 --out chase.wav
   ottoport collections create "Spring campaign"
   ottoport image "spring hero banner" --collection <collection-id>
   ottoport mcp

package/commands/speech.md

@@ -1,5 +1,5 @@
 ---
-description: Turn text into speech, or a prompt into music, through the OttoPort gateway
+description: Turn text into speech, or a prompt into music or sound effects, through the OttoPort gateway
 argument-hint: "<text> [--voice alloy] [--music]"
 allowed-tools: mcp__ottoport__ottoport_generate_speech, mcp__ottoport__ottoport_generate_music, Bash(curl:*)
 ---
@@ -7,7 +7,9 @@ allowed-tools: mcp__ottoport__ottoport_generate_speech, mcp__ottoport__ottoport_
 Request: $ARGUMENTS
 
 Use `ottoport_generate_music` when the request is for music, a song, or a
-backing track; otherwise use `ottoport_generate_speech` to read the text aloud.
+backing track — or for sound effects, ambience or a soundtrack for a video, with
+`model` `mirelo-sfx-2.0` (pass the video as `video_url`, and `duration` as its
+length); otherwise use `ottoport_generate_speech` to read the text aloud.
 Pass `voice` and `format` only when named — speech defaults to `gpt-4o-mini-tts`
 with the `alloy` voice, music to `suno-v5`.
 

package/commands/video.md

@@ -22,6 +22,11 @@ Request: $ARGUMENTS
   discovering it from a failed call.
 - `resolution` is billed: a 1080p or 4k clip costs more per second than the
   model's base tier. Send one only when the request asks for it.
+- When the user wants to preview before paying for the full clip, draft it:
+  `model: "seedance-2.5-draft"` (or `seedance-2.5` with `draft: true`) renders
+  a cheap 480p take. To keep it, call again with the same model and
+  `draft_id` set to the draft's job id — nothing else; it renders that shot in
+  1080p, within seven days.
 - Video generation takes a minute or more and the call blocks until the job is
   terminal. Say so before you start, and do not retry a call that is merely slow
   — a retry is a second billable generation.

package/mcp/server.mjs

@@ -358,7 +358,8 @@ async function generateVideo({ prompt, model, webhook_url, webhook_secret, colle
   const output = job.data?.[0];
   const url = output?.url ? outputLine(output) : undefined;
   // The draft's job id is what completes it, so it is worth saying.
-  if (url && rest.draft) return `${url}\nDraft ${job.id} — complete it at 1080p with draft_id "${job.id}" within seven days.`;
+  // `seedance-2.5-draft` drafts without being told to.
+  if (url && !rest.draft_id && (rest.draft || /-draft$/.test(model ?? ""))) return `${url}\nDraft ${job.id} — complete it at 1080p with draft_id "${job.id}" within seven days.`;
   return url || JSON.stringify(job);
 }
 
@@ -374,15 +375,16 @@ async function videoWebhook({ job_id, action = "status" }) {
   return JSON.stringify({ id: body.id, status: body.status, webhook: body.webhook ?? null }, null, 2);
 }
 
-async function generateAudio(kind, { prompt, model, voice, duration, format, collection }) {
-  if (!prompt) throw new Error("`prompt` is required");
+async function generateAudio(kind, { prompt, model, voice, duration, format, video_url, collection }) {
+  if (!prompt && !video_url) throw new Error("`prompt` is required");
   const res = await fetch(`${BASE}/api/v1/audio/${kind === "tts" ? "speech" : "music"}`, {
     method: "POST",
     headers: headers(),
     body: JSON.stringify({
       model: model || (kind === "tts" ? "gpt-4o-mini-tts" : "suno-v5"),
-      prompt,
+      ...(prompt ? { prompt } : {}),
       ...(voice ? { voice } : {}),
+      ...(video_url ? { video_url } : {}),
       ...(duration ? { duration } : {}),
       ...(format ? { format } : {}),
       ...withCollection(await collectionId(collection)),
@@ -458,7 +460,7 @@ const TOOLS = [
   },
   {
     name: "ottoport_generate_video",
-    description: "Generate a video through an OttoPort video model (Veo, Kling, Seedance, …). Modes: text-to-video, image-to-video (`image_url`), first-and-last-frame (plus `last_frame_url`), reference-to-video (`reference_image_urls`, plus `reference_video_urls` / `reference_audio_urls` on models whose capabilities list `referenceMedia`), and on some models video edit/extend (`video_url`). Seedance 2.5 also drafts: `draft: true` renders a cheap 480p preview, and `draft_id` set to that job's id renders the same shot at 1080p. video-depth-anything instead turns `video_url` into a grayscale depth video and takes no prompt. Kling motion control (`kling-2.6-motion-control`, `kling-3.0-motion-control` and their `-pro` variants) makes the character in `image_url` perform the movement in `video_url`; the prompt is optional and the output runs as long as the clip. Which a model accepts is in its capabilities — call ottoport_list_models. Blocks on the queue and returns a video URL, unless `webhook_url` is given.",
+    description: "Generate a video through an OttoPort video model (Veo, Kling, Seedance, …). Modes: text-to-video, image-to-video (`image_url`), first-and-last-frame (plus `last_frame_url`), reference-to-video (`reference_image_urls`, plus `reference_video_urls` / `reference_audio_urls` on models whose capabilities list `referenceMedia`), and on some models video edit/extend (`video_url`). Seedance 2.5 also drafts: `draft: true` (or the model `seedance-2.5-draft`, where every request is a draft) renders a cheap 480p preview, and `draft_id` set to that job's id renders the same shot at 1080p. video-depth-anything instead turns `video_url` into a grayscale depth video and takes no prompt. Kling motion control (`kling-2.6-motion-control`, `kling-3.0-motion-control` and their `-pro` variants) makes the character in `image_url` perform the movement in `video_url`; the prompt is optional and the output runs as long as the clip. Which a model accepts is in its capabilities — call ottoport_list_models. Blocks on the queue and returns a video URL, unless `webhook_url` is given.",
     inputSchema: {
       type: "object",
       properties: {
@@ -480,8 +482,8 @@ const TOOLS = [
         character_orientation: { type: "string", enum: ["video", "image"], description: "Motion-control models only: whether the character faces the way the person in `video_url` does (\"video\", the default) or keeps the pose of `image_url` (\"image\")." },
         keep_original_sound: { type: "boolean", description: "Motion-control models only: keep the audio of `video_url` in the result." },
         video_task: { type: "string", enum: ["edit", "extend"], description: "edit (default) restyles video_url; extend continues it for `duration` more seconds." },
-        draft: { type: "boolean", description: "Seedance 2.5 only: render a 480p preview at about a quarter of the 1080p price, to check the shot before paying for it. Text, image and reference-image requests; no `resolution`." },
-        draft_id: { type: "string", description: "Seedance 2.5 only: the job id of a finished draft, to render that same shot at 1080p. Send `model` and this alone — prompt, inputs and duration come from the draft. Within seven days of the draft." },
+        draft: { type: "boolean", description: "seedance-2.5 only (implied on seedance-2.5-draft): render a 480p preview at about a quarter of the 1080p price, to check the shot before paying for it. Text, image and reference-image requests; no `resolution`." },
+        draft_id: { type: "string", description: "seedance-2.5 or seedance-2.5-draft: the job id of a finished draft, to render that same shot at 1080p — either id completes a draft made with the other. Send `model` and this alone — prompt, inputs and duration come from the draft. Within seven days of the draft." },
         webhook_url: { type: "string", description: "Public HTTPS endpoint to POST the finished job to (events video.completed / video.failed, signed with HMAC-SHA256). With it the tool returns the job id at once instead of waiting." },
         webhook_secret: { type: "string", description: "Signing secret for webhook_url. Omit to use the server's OTTOPORT_WEBHOOK_SECRET." },
         collection: { type: "string", description: "Save the result for good into this collection — its id or exact name (see ottoport_list_collections). Without it the file expires after a few days. Needs collections unlocked on the account. Defaults to OTTOPORT_COLLECTION when set." },
@@ -521,17 +523,17 @@ const TOOLS = [
   },
   {
     name: "ottoport_generate_music",
-    description: "Generate music from a prompt through an OttoPort music model. Returns an audio URL or data URL.",
+    description: "Generate music or sound effects from a prompt through an OttoPort music model — or, with mirelo-sfx-2.0 and a video_url, a soundtrack synced to that video. Returns an audio URL or data URL.",
     inputSchema: {
       type: "object",
       properties: {
-        prompt: { type: "string", description: "Music-generation prompt." },
-        model: { type: "string", description: "Music model id. Default suno-v5." },
+        prompt: { type: "string", description: "Music-generation prompt, or the sounds to make. Optional with video_url." },
+        model: { type: "string", description: "Music model id. Default suno-v5; mirelo-sfx-2.0 for sound effects." },
         duration: { type: "number", description: "Requested duration in seconds." },
+        video_url: { type: "string", description: "mirelo-sfx-2.0 only: an http(s) video to score. Set duration to its length — duration is what bills." },
         format: { type: "string", description: 'e.g. "mp3" or "wav".' },
         collection: { type: "string", description: "Save the result for good into this collection — its id or exact name (see ottoport_list_collections). Without it the file expires after a few days. Needs collections unlocked on the account. Defaults to OTTOPORT_COLLECTION when set." },
       },
-      required: ["prompt"],
     },
     handler: (args) => generateAudio("music", args),
   },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ottoport",
-  "version": "1.13.1",
+  "version": "1.14.0",
   "description": "Claude Code plugin, CLI and MCP server for OttoPort — one OpenAI-compatible API for every LLM, image, video, and speech model.",
   "homepage": "https://ottoport.ai",
   "repository": {

package/skills/ottoport/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ottoport
-description: Generate text, images, video, speech, and music through OttoPort — one gateway for every model (GPT, Claude, Gemini, GPT Image, Nano Banana, Veo, Kling, Seedance, Suno). Use when the user wants to call an LLM or generate an image, video, or audio and has OttoPort configured, or asks to "use OttoPort".
+description: Generate text, images, video, speech, and music through OttoPort — one gateway for every model (GPT, Claude, Gemini, GPT Image, Nano Banana, Veo, Kling, Seedance, Suno, Mirelo). Use when the user wants to call an LLM or generate an image, video, audio or sound effects and has OttoPort configured, or asks to "use OttoPort".
 ---
 
 # OttoPort
@@ -17,10 +17,10 @@ and do not call the HTTP API, when a tool covers the job:
 | `ottoport_list_models` | The catalog: what each model is for, and its rate in credits and USD. Filter with `modality`, or pass `model` for ONE model in full — its modes, its resolution tiers with prices, and every parameter it reads. |
 | `ottoport_chat` | `prompt`, plus optional `model`, `system`, `temperature`, `max_tokens`. |
 | `ottoport_generate_image` | `prompt`, plus optional `model`, `size` or `resolution`, `quality` (GPT Image and Ideogram), `aspect_ratio`, `n`, `seed`, `image_url` (one reference), `reference_image_urls` (several). Layer decomposition too: `model` `qwen-image-layered` or `seedream-5.0-layers` with `image_url` alone (prompt optional, `num_layers` on Qwen) returns one URL per RGBA layer. |
-| `ottoport_generate_video` | `prompt`, plus optional `model`, `duration`, `resolution`, `aspect_ratio`, `seed`, `image_url` (first frame), `last_frame_url`, `reference_image_urls`, `reference_video_urls` / `reference_audio_urls` (models listing `referenceMedia`), `video_url` (edit / extend, or the movement for motion control), `character_orientation` / `keep_original_sound` (motion control), `draft` / `draft_id` (Seedance 2.5: a 480p preview, then the same shot at 1080p from the preview's job id), `webhook_url` (returns the job id at once and POSTs the result there; the secret comes from `webhook_secret` or the server's `OTTOPORT_WEBHOOK_SECRET`). |
+| `ottoport_generate_video` | `prompt`, plus optional `model`, `duration`, `resolution`, `aspect_ratio`, `seed`, `image_url` (first frame), `last_frame_url`, `reference_image_urls`, `reference_video_urls` / `reference_audio_urls` (models listing `referenceMedia`), `video_url` (edit / extend, or the movement for motion control), `character_orientation` / `keep_original_sound` (motion control), `draft` / `draft_id` (Seedance 2.5: a 480p preview, then the same shot at 1080p from the preview's job id; the model `seedance-2.5-draft` drafts on every request without `draft`), `webhook_url` (returns the job id at once and POSTs the result there; the secret comes from `webhook_secret` or the server's `OTTOPORT_WEBHOOK_SECRET`). |
 | `ottoport_video_webhook` | `job_id`, plus `action` `status` (every delivery attempt and the endpoint's response) or `retry` (redeliver a finished job's webhook now). |
 | `ottoport_generate_speech` | `prompt` (the text), plus optional `model`, `voice`, `format`. |
-| `ottoport_generate_music` | `prompt`, plus optional `model`, `duration`, `format`. |
+| `ottoport_generate_music` | `prompt`, plus optional `model`, `duration`, `format`. Sound effects too: `model` `mirelo-sfx-2.0` makes them from the prompt, or with `video_url` a soundtrack synced to that video, dialogue kept (prompt then optional). It bills per requested second, so set `duration` to the clip's length. |
 | `ottoport_list_collections` | The project's collections (ids, asset counts) and whether this account may save. Read it to find the collection the user means. |
 | `ottoport_create_collection` | `name`, plus optional `description`, `external_id`. |
 | `ottoport_list_assets` | Saved files, optionally by `collection` and `kind`. |
@@ -90,7 +90,7 @@ sensible default.
 | image | `gpt-image-2` | `nano-banana-2.1` (fast generation and edits), `nano-banana-pro` (high fidelity) |
 | video | `kling-3.0` | `seedance-2.0-fast` (cheap), `veo-3.1` (with audio) |
 | speech | `gpt-4o-mini-tts` | `eleven-v3` |
-| music | `suno-v5` | `lyria-2` |
+| music | `suno-v5` | `lyria-2`, `mirelo-sfx-2.0` (sound effects, or a soundtrack for a video) |
 
 Never invent a model id. Call `ottoport_list_models` when unsure — the catalog
 changes, and a wrong id is a failed billable call. Rates come back in credits (the unit the ledger