feat(openai): add transcription, image generation, and fix video sizes

src/ai-sdk/examples/openai-image.ts

@@ -0,0 +1,36 @@
+import { generateImage } from "ai";
+import { openai } from "../index";
+
+async function main() {
+  console.log("generating image with gpt-image-1...");
+  const { images } = await generateImage({
+    model: openai.imageModel("gpt-image-1"),
+    prompt:
+      "a futuristic city at sunset, neon lights reflecting on wet streets",
+    size: "1024x1024",
+  });
+
+  console.log(`image generated: ${images[0]!.uint8Array.byteLength} bytes`);
+  await Bun.write("output/openai-gpt-image.png", images[0]!.uint8Array);
+
+  console.log("\ngenerating with dall-e-3...");
+  const { images: dalleImages } = await generateImage({
+    model: openai.imageModel("dall-e-3"),
+    prompt:
+      "a whimsical treehouse in an enchanted forest, fairy lights, cozy atmosphere",
+    aspectRatio: "16:9",
+    providerOptions: {
+      openai: {
+        quality: "hd",
+        style: "vivid",
+      },
+    },
+  });
+
+  console.log(`dall-e-3 image: ${dalleImages[0]!.uint8Array.byteLength} bytes`);
+  await Bun.write("output/openai-dalle3.png", dalleImages[0]!.uint8Array);
+
+  console.log("\ndone!");
+}
+
+main().catch(console.error);

src/ai-sdk/examples/openai-transcription.ts

@@ -0,0 +1,37 @@
+import { experimental_transcribe as transcribe } from "ai";
+import { openai } from "../index";
+
+async function main() {
+  const audioPath = process.argv[2] || "media/sample-audio.mp3";
+  console.log(`transcribing ${audioPath} with whisper-1...`);
+
+  const audioFile = Bun.file(audioPath);
+  const audioBuffer = await audioFile.arrayBuffer();
+
+  const result = await transcribe({
+    model: openai.transcriptionModel("whisper-1"),
+    audio: new Uint8Array(audioBuffer),
+    providerOptions: {
+      openai: {
+        language: "en",
+        timestamp_granularities: ["segment"],
+      },
+    },
+  });
+
+  console.log("\ntranscription:");
+  console.log(result.text);
+
+  if (result.segments && result.segments.length > 0) {
+    console.log("\nsegments:");
+    for (const segment of result.segments) {
+      console.log(
+        `  [${segment.startSecond.toFixed(2)}s - ${segment.endSecond.toFixed(2)}s] ${segment.text}`,
+      );
+    }
+  }
+
+  console.log("\ndone!");
+}
+
+main().catch(console.error);