vargai 0.4.0-alpha100 → 0.4.0-alpha101

package/README.md

@@ -315,6 +315,13 @@ See the [BYOK docs](https://docs.varg.ai/sdk/byok) for details.
 
 A typical 3-clip video costs $2-5. Cache hits are always free.
 
+## Star History
+
+<img width="2832" height="2253" alt="star-history-202643" src="https://github.com/user-attachments/assets/63e84279-d756-43a9-b328-118fb69ed2d5" />
+
+
+
+
 ## Contributing
 
 See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup.

package/package.json

@@ -104,7 +104,7 @@
   "license": "Apache-2.0",
   "author": "varg.ai <hello@varg.ai> (https://varg.ai)",
   "sideEffects": false,
-  "version": "0.4.0-alpha100",
+  "version": "0.4.0-alpha101",
   "exports": {
     ".": "./src/index.ts",
     "./ai": "./src/ai-sdk/index.ts",

package/src/ai-sdk/file.ts

@@ -17,6 +17,8 @@ export interface FileMetadata {
   model?: string;
   /** Original prompt used */
   prompt?: string;
+  /** Duration in seconds (for video/audio files) */
+  duration?: number;
 }
 
 export class File {
@@ -158,11 +160,16 @@ export class File {
     return this._url;
   }
 
-  /** Get file metadata (type, model, prompt) */
+  /** Get file metadata (type, model, prompt, duration) */
   get metadata(): FileMetadata {
     return this._metadata;
   }
 
+  /** Duration in seconds (for video/audio files) */
+  get duration(): number | undefined {
+    return this._metadata.duration;
+  }
+
   /** Set metadata and return this for chaining */
   withMetadata(metadata: FileMetadata): this {
     this._metadata = { ...this._metadata, ...metadata };

package/src/ai-sdk/providers/editly/index.ts

@@ -99,12 +99,34 @@ async function processClips(
     let duration = clip.duration ?? defaultDuration;
 
     for (const layer of layers) {
-      if (layer.type === "video" && !clip.duration) {
+      if (layer.type === "video") {
         const videoLayer = layer as VideoLayer;
-        const videoDuration = await getVideoDuration(videoLayer.path, backend);
+
+        // Use pre-propagated duration when available (avoids ffprobe HTTP
+        // round-trip for remote URLs). Fall back to ffprobe otherwise.
+        const videoDuration =
+          videoLayer.sourceDuration ??
+          (await getVideoDuration(videoLayer.path, backend));
+
         const cutFrom = videoLayer.cutFrom ?? 0;
-        const cutTo = videoLayer.cutTo ?? videoDuration;
-        duration = cutTo - cutFrom;
+        const cutTo = Math.min(
+          videoLayer.cutTo ?? videoDuration,
+          videoDuration,
+        );
+
+        // Clamp the layer's cutTo so the FFmpeg trim filter also respects
+        // the actual source duration (prevents freeze frames at the tail)
+        videoLayer.cutTo = cutTo;
+
+        const effectiveDuration = cutTo - cutFrom;
+        if (!clip.duration) {
+          // No explicit duration — derive from the video layer
+          duration = effectiveDuration;
+        } else if (effectiveDuration < duration) {
+          // Explicit duration exceeds actual video length — clamp to avoid
+          // freeze frames and xfade offset misalignment
+          duration = effectiveDuration;
+        }
         break;
       }
     }

package/src/ai-sdk/providers/editly/types.ts

@@ -117,6 +117,8 @@ export interface VideoLayer extends BaseLayer {
   cropPosition?: CropPosition;
   cutFrom?: number;
   cutTo?: number;
+  /** Known source video duration in seconds (avoids ffprobe when set). */
+  sourceDuration?: number;
   width?: SizeValue;
   height?: SizeValue;
   left?: SizeValue;

package/src/ai-sdk/providers/elevenlabs.ts

@@ -21,16 +21,30 @@ import type { MusicModelV3, MusicModelV3CallOptions } from "../music-model";
  * call the gateway's GET /v1/voices endpoint to browse/search.
  */
 const VOICES: Record<string, string> = {
-  rachel: "21m00Tcm4TlvDq8ikWAM",
-  domi: "AZnzlk1XvdvUeBnXmlld",
-  sarah: "EXAVITQu4vr4xnSDxMaL",
-  bella: "EXAVITQu4vr4xnSDxMaL", // alias — ElevenLabs calls this voice "Sarah"
-  antoni: "ErXwobaYiN019PkySvjV",
-  elli: "MF3mGyEYCl7XYWbV9V6O",
-  josh: "TxGEqnHWrfWFTfGW9XjX",
-  arnold: "VR6AewLTigWG4xSOukaG",
+  // Current ElevenLabs premade voices (source: skills/varg-ai/references/models.md)
   adam: "pNInz6obpgDQGcFmaJgB",
-  sam: "yoZ06aMxZJJ28mfd3POQ",
+  alice: "Xb7hH8MSUJpSbSDYk0k2",
+  bella: "hpp4J3VqNfWAUOO0d1Us",
+  bill: "pqHfZKP75CvOlQylNhV4",
+  brian: "nPczCjzI2devNBz1zQrb",
+  callum: "N2lVS1w4EtoT3dr4eOWO",
+  charlie: "IKne3meq5aSn9XLyUdCD",
+  chris: "iP95p4xoKVk53GoZ742B",
+  daniel: "onwK4e9ZLuTAKqWW03F9",
+  eric: "cjVigY5qzO86Huf0OWal",
+  george: "JBFqnCBsd6RMkjVDRZzb",
+  harry: "SOYHLrjzK2X1ezoPC6cr",
+  jessica: "cgSgspJ2msm6clMCkdW9",
+  laura: "FGY2WhTYpPnrIDTdsKH5",
+  liam: "TX3LPaxmHKxFdv7VOQHJ",
+  lily: "pFZP5JQG7iQjIQuC4Bku",
+  matilda: "XrExE9yKIg1WjnnlVkGX",
+  river: "SAz9YHcvj6GT2YYXdXww",
+  roger: "CwhRBWXzGAHq8TQ4Fs17",
+  sarah: "EXAVITQu4vr4xnSDxMaL",
+  will: "bIHbv24MWmeRgasZH58o",
+  // Legacy
+  rachel: "21m00Tcm4TlvDq8ikWAM",
 };
 
 const TTS_MODELS: Record<string, string> = {

package/src/ai-sdk/providers/fal.ts

@@ -15,6 +15,7 @@ import pMap from "p-map";
 import type { CacheStorage } from "../cache";
 import { fileCache } from "../file-cache";
 import type { VideoModelV3, VideoModelV3CallOptions } from "../video-model";
+import { normalizeProviderInput } from "./model-rules";
 
 interface PendingRequest {
   request_id: string;
@@ -640,35 +641,22 @@ class FalVideoModel implements VideoModelV3 {
         if (input.video_size === undefined) {
           input.video_size = "auto";
         }
-      } else if (isKlingV3 || isKlingV26) {
-        // Duration must be string for Kling v2.6+ and O3 (v3)
-        input.duration = String(duration ?? 5);
-      } else if (isGrokImagine) {
-        // Grok Imagine: duration 1-15 seconds (default 6)
-        input.duration = duration ?? 6;
-        // Grok Imagine supports resolution: "480p", "720p" (default "720p")
-        if (!input.resolution) {
-          input.resolution = "720p";
-        }
-      } else if (isSora2) {
-        // Sora 2: only supports 4, 8, 12, 16, 20 second durations
-        const allowedDurations = [4, 8, 12, 16, 20];
-        const d = duration ?? 4;
-        if (!allowedDurations.includes(d)) {
-          warnings.push({
-            type: "other",
-            message: `Sora 2 only supports durations: ${allowedDurations.join(", ")}s. Got ${d}s, defaulting to 4s.`,
-          });
-          input.duration = 4;
-        } else {
-          input.duration = d;
-        }
-        // Disable video deletion so generated video URLs remain accessible
-        if (input.delete_video === undefined) {
-          input.delete_video = false;
-        }
       } else {
-        input.duration = duration ?? 5;
+        // Apply model-specific duration normalization via Zod schemas
+        // (clamp to valid range, round floats, convert type e.g. number → string for Kling v3)
+        const normalized = normalizeProviderInput(this.modelId, { duration });
+        input.duration = normalized.duration;
+
+        // Model-specific non-duration defaults
+        if (isGrokImagine) {
+          if (!input.resolution) {
+            input.resolution = "720p";
+          }
+        } else if (isSora2) {
+          if (input.delete_video === undefined) {
+            input.delete_video = false;
+          }
+        }
       }
 
       if (hasImageInput && files) {

package/src/ai-sdk/providers/model-rules.ts

@@ -0,0 +1,129 @@
+/**
+ * Per-model provider input validation schemas.
+ *
+ * Each model that has provider-specific input constraints (duration format,
+ * allowed ranges, type coercion) gets a Zod schema here. The schemas use
+ * `.transform()` to auto-fix invalid inputs — rounding floats, clamping to
+ * valid ranges, and converting types (e.g. number → string for Kling v3).
+ *
+ * Usage:
+ *   const fixed = normalizeProviderInput("kling-v3", { duration: 2.34 });
+ *   // → { duration: "3" }  (rounded to 2, clamped to min 3, stringified)
+ *
+ * NOTE: This file is kept in sync with gateway/packages/schemas/src/model-rules.ts.
+ *       When adding new model rules, update both files.
+ */
+
+import { z } from "zod";
+
+// ---------------------------------------------------------------------------
+// Duration schema builders
+// ---------------------------------------------------------------------------
+
+/** Duration as string integer clamped to [min, max]. Accepts number, outputs string. */
+function stringIntDuration(min: number, max: number, defaultVal: number) {
+  return z
+    .number()
+    .optional()
+    .transform((v) =>
+      String(Math.max(min, Math.min(max, Math.round(v ?? defaultVal)))),
+    );
+}
+
+/** Duration snapped to nearest allowed value. Accepts number, outputs number. */
+function enumDuration(allowed: number[], defaultVal: number) {
+  return z
+    .number()
+    .optional()
+    .transform((v) => {
+      const raw = v ?? defaultVal;
+      return allowed.reduce((prev, curr) =>
+        Math.abs(curr - raw) < Math.abs(prev - raw) ? curr : prev,
+      );
+    });
+}
+
+/** Duration as integer clamped to [min, max]. Accepts number, outputs number. */
+function rangeDuration(min: number, max: number, defaultVal: number) {
+  return z
+    .number()
+    .optional()
+    .transform((v) =>
+      Math.max(min, Math.min(max, Math.round(v ?? defaultVal))),
+    );
+}
+
+/** Passthrough duration rounded to integer. */
+function intDuration(defaultVal: number) {
+  return z
+    .number()
+    .optional()
+    .transform((v) => Math.round(v ?? defaultVal));
+}
+
+// ---------------------------------------------------------------------------
+// Per-model provider input schemas
+// ---------------------------------------------------------------------------
+
+const ModelDurationRules: Record<string, z.ZodType> = {
+  // Kling O3 (v3): fal expects string integer "3"–"15"
+  "kling-v3": z.object({ duration: stringIntDuration(3, 15, 5) }),
+  "kling-v3-standard": z.object({ duration: stringIntDuration(3, 15, 5) }),
+
+  // Kling v2.6: same rules as v3
+  "kling-v2.6": z.object({ duration: stringIntDuration(3, 15, 5) }),
+
+  // Kling legacy: exactly 5 or 10
+  "kling-v2.5": z.object({ duration: enumDuration([5, 10], 5) }),
+  "kling-v2.1": z.object({ duration: enumDuration([5, 10], 5) }),
+  "kling-v2": z.object({ duration: enumDuration([5, 10], 5) }),
+
+  // Wan: 5 or 10
+  "wan-2.5": z.object({ duration: enumDuration([5, 10], 5) }),
+  "wan-2.5-preview": z.object({ duration: enumDuration([5, 10], 5) }),
+
+  // Minimax: round to integer
+  minimax: z.object({ duration: intDuration(5) }),
+
+  // Grok Imagine: integer 1–15
+  "grok-imagine": z.object({ duration: rangeDuration(1, 15, 6) }),
+
+  // Sora 2: only 4, 8, 12, 16, 20
+  "sora-2": z.object({ duration: enumDuration([4, 8, 12, 16, 20], 4) }),
+  "sora-2-pro": z.object({ duration: enumDuration([4, 8, 12, 16, 20], 4) }),
+
+  // Seedance (piapi): 5, 10, or 15
+  "seedance-2-preview": z.object({ duration: enumDuration([5, 10, 15], 5) }),
+  "seedance-2-fast-preview": z.object({
+    duration: enumDuration([5, 10, 15], 5),
+  }),
+};
+
+// ---------------------------------------------------------------------------
+// Public API
+// ---------------------------------------------------------------------------
+
+/**
+ * Normalize provider input for a given model.
+ *
+ * Validates and transforms fields (currently `duration`) to match what the
+ * provider API expects — correct type, clamped to valid range, rounded to
+ * integer.
+ *
+ * - Unknown models: input returned as-is (passthrough).
+ * - Parse failures: input returned as-is (defensive — never throws).
+ */
+export function normalizeProviderInput(
+  model: string,
+  input: Record<string, unknown>,
+): Record<string, unknown> {
+  const schema = ModelDurationRules[model];
+  if (!schema) return input;
+
+  const result = schema.safeParse({ duration: input.duration });
+  if (!result.success) return input;
+
+  return { ...input, ...(result.data as Record<string, unknown>) };
+}
+
+export { ModelDurationRules };

package/src/definitions/actions/voice.ts

@@ -62,16 +62,30 @@ export interface VoiceResult {
 
 // Voice name to ID mapping. Unknown names pass through as voice_ids.
 const VOICE_MAP: Record<string, string> = {
-  rachel: VOICES.RACHEL,
-  domi: VOICES.DOMI,
-  sarah: VOICES.SARAH,
-  bella: VOICES.BELLA,
-  antoni: VOICES.ANTONI,
-  elli: VOICES.ELLI,
-  josh: VOICES.JOSH,
-  arnold: VOICES.ARNOLD,
+  // Current ElevenLabs premade voices (source: skills/varg-ai/references/models.md)
   adam: VOICES.ADAM,
-  sam: VOICES.SAM,
+  alice: VOICES.ALICE,
+  bella: VOICES.BELLA,
+  bill: VOICES.BILL,
+  brian: VOICES.BRIAN,
+  callum: VOICES.CALLUM,
+  charlie: VOICES.CHARLIE,
+  chris: VOICES.CHRIS,
+  daniel: VOICES.DANIEL,
+  eric: VOICES.ERIC,
+  george: VOICES.GEORGE,
+  harry: VOICES.HARRY,
+  jessica: VOICES.JESSICA,
+  laura: VOICES.LAURA,
+  liam: VOICES.LIAM,
+  lily: VOICES.LILY,
+  matilda: VOICES.MATILDA,
+  river: VOICES.RIVER,
+  roger: VOICES.ROGER,
+  sarah: VOICES.SARAH,
+  will: VOICES.WILL,
+  // Legacy
+  rachel: VOICES.RACHEL,
 };
 
 export async function generateVoice(

package/src/providers/elevenlabs.ts

@@ -192,16 +192,30 @@ export class ElevenLabsProvider extends BaseProvider {
  * call the gateway's GET /v1/voices endpoint to browse/search.
  */
 export const VOICES = {
-  RACHEL: "21m00Tcm4TlvDq8ikWAM",
-  DOMI: "AZnzlk1XvdvUeBnXmlld",
-  SARAH: "EXAVITQu4vr4xnSDxMaL",
-  BELLA: "EXAVITQu4vr4xnSDxMaL", // alias — ElevenLabs calls this voice "Sarah"
-  ANTONI: "ErXwobaYiN019PkySvjV",
-  ELLI: "MF3mGyEYCl7XYWbV9V6O",
-  JOSH: "TxGEqnHWrfWFTfGW9XjX",
-  ARNOLD: "VR6AewLTigWG4xSOukaG",
+  // Current ElevenLabs premade voices (source: skills/varg-ai/references/models.md)
   ADAM: "pNInz6obpgDQGcFmaJgB",
-  SAM: "yoZ06aMxZJJ28mfd3POQ",
+  ALICE: "Xb7hH8MSUJpSbSDYk0k2",
+  BELLA: "hpp4J3VqNfWAUOO0d1Us",
+  BILL: "pqHfZKP75CvOlQylNhV4",
+  BRIAN: "nPczCjzI2devNBz1zQrb",
+  CALLUM: "N2lVS1w4EtoT3dr4eOWO",
+  CHARLIE: "IKne3meq5aSn9XLyUdCD",
+  CHRIS: "iP95p4xoKVk53GoZ742B",
+  DANIEL: "onwK4e9ZLuTAKqWW03F9",
+  ERIC: "cjVigY5qzO86Huf0OWal",
+  GEORGE: "JBFqnCBsd6RMkjVDRZzb",
+  HARRY: "SOYHLrjzK2X1ezoPC6cr",
+  JESSICA: "cgSgspJ2msm6clMCkdW9",
+  LAURA: "FGY2WhTYpPnrIDTdsKH5",
+  LIAM: "TX3LPaxmHKxFdv7VOQHJ",
+  LILY: "pFZP5JQG7iQjIQuC4Bku",
+  MATILDA: "XrExE9yKIg1WjnnlVkGX",
+  RIVER: "SAz9YHcvj6GT2YYXdXww",
+  ROGER: "CwhRBWXzGAHq8TQ4Fs17",
+  SARAH: "EXAVITQu4vr4xnSDxMaL",
+  WILL: "bIHbv24MWmeRgasZH58o",
+  // Legacy
+  RACHEL: "21m00Tcm4TlvDq8ikWAM",
 };
 
 // Export singleton instance (lazy initialization means no error on import)

package/src/react/renderers/clip.ts

@@ -92,24 +92,25 @@ async function renderClipLayers(
         const props = element.props as VideoProps;
         pending.push({
           type: "async",
-          promise: renderVideo(element as VargElement<"video">, ctx)
-            .then((file) => ctx.backend.resolvePath(file))
-            .then(
-              (path) =>
-                ({
-                  type: "video",
-                  path,
-                  resizeMode: props.resize,
-                  cropPosition: props.cropPosition,
-                  cutFrom: props.cutFrom ?? clipOptions?.cutFrom,
-                  cutTo: props.cutTo ?? clipOptions?.cutTo,
-                  mixVolume: props.keepAudio ? (props.volume ?? 1) : 0,
-                  left: props.left,
-                  top: props.top,
-                  width: props.width,
-                  height: props.height,
-                }) as VideoLayer,
-            ),
+          promise: renderVideo(element as VargElement<"video">, ctx).then(
+            async (file) => {
+              const path = await ctx.backend.resolvePath(file);
+              return {
+                type: "video",
+                path,
+                sourceDuration: file.duration,
+                resizeMode: props.resize,
+                cropPosition: props.cropPosition,
+                cutFrom: props.cutFrom ?? clipOptions?.cutFrom,
+                cutTo: props.cutTo ?? clipOptions?.cutTo,
+                mixVolume: props.keepAudio ? (props.volume ?? 1) : 0,
+                left: props.left,
+                top: props.top,
+                width: props.width,
+                height: props.height,
+              } as VideoLayer;
+            },
+          ),
         });
         break;
       }
@@ -158,17 +159,16 @@ async function renderClipLayers(
           promise: renderTalkingHead(
             element as VargElement<"talking-head">,
             ctx,
-          )
-            .then((file) => ctx.backend.resolvePath(file))
-            .then(
-              (path) =>
-                ({
-                  type: "video",
-                  path,
-                  resizeMode: "cover",
-                  mixVolume: 1,
-                }) as VideoLayer,
-            ),
+          ).then(async (file) => {
+            const path = await ctx.backend.resolvePath(file);
+            return {
+              type: "video",
+              path,
+              sourceDuration: file.duration,
+              resizeMode: "cover",
+              mixVolume: 1,
+            } as VideoLayer;
+          }),
         });
         break;
       }

package/src/react/renderers/video.ts

@@ -170,6 +170,7 @@ export async function renderVideo(
       type: "video",
       model: modelId,
       prompt: promptText,
+      duration: props.duration,
     });
 
     if (!file.url && ctx.storage) {