videodraft 0.2.1 → 0.3.1

package/dist/client.d.ts

@@ -38,6 +38,13 @@ declare class VideoDraftClient {
     get endpoint(): string;
     rpc<T = any>(method: string, params?: unknown): Promise<T>;
     private post;
+    /**
+     * Make an authenticated REST request to a non-MCP API route (e.g.
+     * /api/elevenlabs-key, which manages the user's BYOK ElevenLabs key and has no
+     * MCP tool by design). Uses the same bearer token + 401 refresh as rpc().
+     * Returns the parsed JSON body; throws on non-2xx with the server's error.
+     */
+    restRequest<T = any>(method: string, path: string, body?: unknown): Promise<T>;
     /**
      * Batch several JSON-RPC requests into ONE HTTP round trip (the server
      * implements JSON-RPC 2.0 batching). With N concurrent jobs this turns N

package/dist/client.js

@@ -264,6 +264,43 @@ var VideoDraftClient = class {
       signal: AbortSignal.timeout(this.requestTimeoutMs)
     });
   }
+  /**
+   * Make an authenticated REST request to a non-MCP API route (e.g.
+   * /api/elevenlabs-key, which manages the user's BYOK ElevenLabs key and has no
+   * MCP tool by design). Uses the same bearer token + 401 refresh as rpc().
+   * Returns the parsed JSON body; throws on non-2xx with the server's error.
+   */
+  async restRequest(method, path4, body) {
+    const doFetch = (token2) => this.fetchImpl(`${this.baseUrl}${path4}`, {
+      method,
+      headers: {
+        "content-type": "application/json",
+        authorization: `Bearer ${token2}`,
+        "user-agent": this.userAgent
+      },
+      ...body === void 0 ? {} : { body: JSON.stringify(body) },
+      signal: AbortSignal.timeout(this.requestTimeoutMs)
+    });
+    const token = await this.tokenProvider.getAccessToken();
+    let response = await doFetch(token);
+    if (response.status === 401 && this.tokenProvider.onUnauthorized) {
+      const fresh = await this.tokenProvider.onUnauthorized();
+      if (fresh) response = await doFetch(fresh);
+    }
+    if (response.status === 401) {
+      throw new AuthError("Token is invalid, expired, or revoked.");
+    }
+    let parsed = null;
+    try {
+      parsed = await response.json();
+    } catch {
+    }
+    if (!response.ok) {
+      const detail = parsed?.error?.message ?? parsed?.error ?? `HTTP ${response.status}`;
+      throw new RpcError(response.status, detail);
+    }
+    return parsed;
+  }
   /**
    * Batch several JSON-RPC requests into ONE HTTP round trip (the server
    * implements JSON-RPC 2.0 batching). With N concurrent jobs this turns N

package/dist/index.js

@@ -24,8 +24,8 @@ function readVersionFromDisk() {
   }
 }
 function resolveVersion() {
-  if ("0.2.1") {
-    return "0.2.1";
+  if ("0.3.1") {
+    return "0.3.1";
   }
   return readVersionFromDisk();
 }
@@ -691,6 +691,43 @@ var VideoDraftClient = class {
       signal: AbortSignal.timeout(this.requestTimeoutMs)
     });
   }
+  /**
+   * Make an authenticated REST request to a non-MCP API route (e.g.
+   * /api/elevenlabs-key, which manages the user's BYOK ElevenLabs key and has no
+   * MCP tool by design). Uses the same bearer token + 401 refresh as rpc().
+   * Returns the parsed JSON body; throws on non-2xx with the server's error.
+   */
+  async restRequest(method, path5, body) {
+    const doFetch = (token2) => this.fetchImpl(`${this.baseUrl}${path5}`, {
+      method,
+      headers: {
+        "content-type": "application/json",
+        authorization: `Bearer ${token2}`,
+        "user-agent": this.userAgent
+      },
+      ...body === void 0 ? {} : { body: JSON.stringify(body) },
+      signal: AbortSignal.timeout(this.requestTimeoutMs)
+    });
+    const token = await this.tokenProvider.getAccessToken();
+    let response = await doFetch(token);
+    if (response.status === 401 && this.tokenProvider.onUnauthorized) {
+      const fresh = await this.tokenProvider.onUnauthorized();
+      if (fresh) response = await doFetch(fresh);
+    }
+    if (response.status === 401) {
+      throw new AuthError("Token is invalid, expired, or revoked.");
+    }
+    let parsed = null;
+    try {
+      parsed = await response.json();
+    } catch {
+    }
+    if (!response.ok) {
+      const detail = parsed?.error?.message ?? parsed?.error ?? `HTTP ${response.status}`;
+      throw new RpcError(response.status, detail);
+    }
+    return parsed;
+  }
   /**
    * Batch several JSON-RPC requests into ONE HTTP round trip (the server
    * implements JSON-RPC 2.0 batching). With N concurrent jobs this turns N
@@ -1057,6 +1094,127 @@ ${fmt.bold(ctxOut, "Open this URL to log in:")}
       ]);
     });
   });
+  const el = program.command("elevenlabs").description("Manage your ElevenLabs API key (BYOK) \u2014 use your cloned voices");
+  el.command("status").description("Show whether your ElevenLabs key is connected and active").action(async function() {
+    const ctx = buildContext(this);
+    const st = await ctx.client.restRequest("GET", "/api/elevenlabs-key");
+    emit(ctx.out, st, (o) => {
+      kv(o, [
+        ["Connected", st?.hasKey ? `yes (\u2022\u2022\u2022\u2022${st.hint ?? ""})` : "no"],
+        ["Active", st?.enabled ? "yes" : "no"],
+        ["Server", ctx.baseUrl]
+      ]);
+      if (!st?.hasKey) {
+        note(
+          o,
+          fmt.dim(o, "Connect one: videodraft elevenlabs set --key <xi-...>")
+        );
+      }
+    });
+  });
+  el.command("set").description("Connect (or replace) your ElevenLabs API key and activate it").option("--key <key>", "your ElevenLabs API key (xi-...)").option("--no-enable", "store the key without turning it on").action(async function() {
+    const opts = this.opts();
+    const ctx = buildContext(this);
+    let key = opts.key?.trim();
+    if (!key && !process.stdin.isTTY) key = (await readStdin()).trim();
+    if (!key) {
+      throw new CliError(
+        "Provide your key with --key <xi-...> (or pipe it via stdin).",
+        EXIT.USAGE
+      );
+    }
+    const spin = spinner(ctx.out, "Validating key with ElevenLabs\u2026");
+    try {
+      const res = await ctx.client.restRequest(
+        "POST",
+        "/api/elevenlabs-key",
+        { key, enabled: opts.enable !== false }
+      );
+      spin.stop();
+      capture("cli_elevenlabs_set");
+      emit(
+        ctx.out,
+        res,
+        (o) => note(
+          o,
+          fmt.green(
+            o,
+            `ElevenLabs key saved (\u2022\u2022\u2022\u2022${res.hint ?? ""})${res.enabled ? " and active \u2014 your cloned voices are ready." : " \u2014 run `videodraft elevenlabs enable` to turn it on."}`
+          )
+        )
+      );
+    } catch (e) {
+      spin.stop();
+      throw e;
+    }
+  });
+  el.command("enable").description("Turn your ElevenLabs key on").action(async function() {
+    const ctx = buildContext(this);
+    const res = await ctx.client.restRequest(
+      "PATCH",
+      "/api/elevenlabs-key",
+      { enabled: true }
+    );
+    emit(
+      ctx.out,
+      res,
+      (o) => note(o, fmt.green(o, "ElevenLabs key is now active."))
+    );
+  });
+  el.command("disable").description("Turn your ElevenLabs key off (use VideoDraft credits again)").action(async function() {
+    const ctx = buildContext(this);
+    const res = await ctx.client.restRequest(
+      "PATCH",
+      "/api/elevenlabs-key",
+      { enabled: false }
+    );
+    emit(
+      ctx.out,
+      res,
+      (o) => note(
+        o,
+        "ElevenLabs key disabled. ElevenLabs generations use the VideoDraft path."
+      )
+    );
+  });
+  el.command("remove").description("Delete your stored ElevenLabs API key").action(async function() {
+    const ctx = buildContext(this);
+    const res = await ctx.client.restRequest(
+      "DELETE",
+      "/api/elevenlabs-key"
+    );
+    capture("cli_elevenlabs_remove");
+    emit(
+      ctx.out,
+      res ?? { ok: true },
+      (o) => note(o, "ElevenLabs key removed.")
+    );
+  });
+  el.command("voices").description("List your ElevenLabs cloned/professional voices").action(async function() {
+    const ctx = buildContext(this);
+    const res = await ctx.client.callTool("list_cloned_voices");
+    emit(ctx.out, res, (o) => {
+      if (!res?.byok_active) {
+        note(
+          o,
+          fmt.dim(
+            o,
+            res?.hint ?? "Connect your ElevenLabs key first: videodraft elevenlabs set --key <xi-...>"
+          )
+        );
+        return;
+      }
+      const voices = res?.voices ?? [];
+      if (!voices.length) {
+        note(o, "No cloned voices in your ElevenLabs account yet.");
+        return;
+      }
+      kv(
+        o,
+        voices.map((v) => [v.name, v.id])
+      );
+    });
+  });
 }
 
 // src/commands/account.ts
@@ -1749,7 +1907,7 @@ function registerGenerateCommands(program) {
   generate.command("video [prompt...]").description("Generate a video clip (async; per-second pricing \u2014 see --estimate)").option("--model <id>", "video model id (default google-veo3.1 fast)").option("--ar <ratio>", 'aspect ratio, e.g. "16:9", "9:16"').option("--duration <seconds>", "clip duration in seconds").option("--resolution <res>", 'e.g. "480p", "720p", "1080p", "4k"').option(
     "--quality <tier>",
     'e.g. "mini", "fast", "standard", "quality", "pro"'
-  ).option("--audio", "generate native model audio").option("--no-audio", "disable native model audio").option("--start-image <url|file>", "start frame (image-to-video)").option("--end-image <url|file>", "end frame (supported models only)").option("--ref <url|file>", "reference image (repeatable)", collect, []).option("--ref-video <url|file>", "reference video (repeatable; Seedance 2, Wan 2.7; local files uploaded)", collect, []).option("--ref-audio <url|file>", "reference audio (repeatable; Seedance 2; local files uploaded)", collect, []).option("--segment <prompt:seconds>", "multi-prompt segment (repeatable; Kling 3.0 / 3.0 Turbo / O3)", collect, []).option("--negative <text>", "negative prompt (Kling/Wan/Luma)").option("--seed <n>", "seed").option("--project <id>", "attach to a project").option("--session <id>", "AI Studio session id").option("--scene <n>", "0-based scene index").option("--shot <n>", "0-based shot index").option("--download <path>", "download outputs (template: {job_id} {index} {ext})").option("--no-wait", "submit and return the job id immediately").option("--estimate", "print the cost estimate and exit (spends nothing)").action(async function(promptWords = []) {
+  ).option("--audio", "generate native model audio").option("--no-audio", "disable native model audio").option("--start-image <url|file>", "start frame (image-to-video)").option("--end-image <url|file>", "end frame (supported models only)").option("--ref <url|file>", "reference image (repeatable)", collect, []).option("--ref-video <url|file>", "reference video (repeatable; Gemini Omni Flash, Seedance 2, Kling O3, Wan 2.7; local files uploaded)", collect, []).option("--ref-audio <url|file>", "reference audio (repeatable; Seedance 2; local files uploaded)", collect, []).option("--segment <prompt:seconds>", "multi-prompt segment (repeatable; Kling 3.0 / 3.0 Turbo / O3)", collect, []).option("--negative <text>", "negative prompt (Kling/Wan/Luma)").option("--seed <n>", "seed").option("--project <id>", "attach to a project").option("--session <id>", "AI Studio session id").option("--scene <n>", "0-based scene index").option("--shot <n>", "0-based shot index").option("--download <path>", "download outputs (template: {job_id} {index} {ext})").option("--no-wait", "submit and return the job id immediately").option("--estimate", "print the cost estimate and exit (spends nothing)").action(async function(promptWords = []) {
     const ctx = buildContext(this);
     const opts = this.opts();
     const prompt = promptWords.join(" ").trim();

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "videodraft",
-  "version": "0.2.1",
+  "version": "0.3.1",
   "description": "Official VideoDraft CLI — create AI videos, images and audio from your terminal. Agent-friendly: --json everywhere, stable exit codes, async job polling.",
   "license": "MIT",
   "type": "module",

package/skills/videodraft/references/models.md

@@ -12,8 +12,8 @@ videodraft models styles --json    # visual style presets
 
 ## Defaults (safe starting points)
 
-- **Image**: `nano-banana-2` (the platform default, 1K). Use `--num 1..4` for variations of one prompt in a single call — never loop for variations.
-- **Video**: `google-veo3.1` at fast quality (6s / 720p) — the platform default.
+- **Image**: `nano-banana-2` (the platform default, 1K, up to 14 reference images). Use `--num 1..4` for variations of one prompt in a single call — never loop for variations. `nano-banana-2-lite` is the fastest/cheapest Google direct image model (1K only, up to 14 reference images).
+- **Video**: `google-veo3.1` at fast quality (6s / 720p) — the platform default. `gemini-omni-flash` is Google's any-to-any multimodal video model (text/image/video → video, auto or 3-10s, 720p, audio always on).
 - **Voiceover**: ElevenLabs Brittney (default voice).
 - **Music**: `lyria-3-clip-preview` (30s, cheap); `lyria-3-pro-preview` for 180s/quality; `elevenlabs-music` for music that can include vocals/lyrics.
 - **ElevenLabs audio**: `generate sound-effect`, `generate dialogue`, `generate voice-changer`, and `generate dub` are synchronous audio/media calls. Voice changer and dubbing require the source media duration in seconds for billing and currently accept source media up to 300s.
@@ -24,7 +24,7 @@ videodraft models styles --json    # visual style presets
 - Most video models support only 16:9 / 9:16 / 1:1. A 3:4 request hard-fails on most.
 - `--seed` reproduces a specific output on models that support it (e.g. Flux, Ideogram V4); everything else ignores it. You do not need a seed for variation — `--num` already varies.
 - `--rendering-speed` applies to Ideogram (V3: `Default`/`Turbo`/`Quality`; V4: `Turbo`/`Balanced`/`Quality`) and affects image cost — pass it to `videodraft costs ... --rendering-speed <tier>` for an accurate estimate. Always trust `videodraft models image --json` over this list; new models and tiers appear there the moment the platform ships them, with no CLI update.
-- Reference inputs: `--ref <img>` (images), `--ref-video <v>` (Seedance 2, Wan 2.7), `--ref-audio <a>` (Seedance 2). The CLI uploads local files for all of these, so you can pass a path or a URL. `--segment "<prompt>:<seconds>"` (repeatable) drives multi-prompt models (Kling 3.0 / 3.0 Turbo / O3); total 3-15s. `generate image --video-ref` is the nano-banana-2 video reference.
+- Reference inputs: `--ref <img>` (images), `--ref-video <v>` (Gemini Omni Flash, Seedance 2, Kling O3, Wan 2.7), `--ref-audio <a>` (Seedance 2). The CLI uploads local files for all of these, so you can pass a path or a URL. `--segment "<prompt>:<seconds>"` (repeatable) drives multi-prompt models (Kling 3.0 / 3.0 Turbo / O3); total 3-15s. `generate image --video-ref` is the nano-banana-2 video reference.
 - The top-level prompt is OPTIONAL for `generate video` with multi-prompt models and for Kling 3.0 Turbo (`--model kling-v3-turbo`) image-to-video — a `--segment`-only or `--start-image`-only call is valid. Every other model still needs a prompt; the server enforces per-model rules.
 - AI Production: `videodraft produce <project> --mode full_video` generates one Seedance 2 video per scene; poll with `videodraft generations`, then `videodraft finalize <project>` swaps them into the timeline before `export`.