Whisper-large-v3-turbo с Cloudflare Workers AI

cd whisper-tutorial

import { Buffer } from "node:buffer";
import type { Ai } from "workers-ai";

export interface Env {
	AI: Ai;
	// If needed, add your KV namespace for storing transcripts.
	// MY_KV_NAMESPACE: KVNamespace;
}

/**
 * Fetches the audio file from the provided URL and splits it into chunks.
 * This function explicitly follows redirects.
 *
 * @param audioUrl - The URL of the audio file.
 * @returns An array of ArrayBuffers, each representing a chunk of the audio.
 */
async function getAudioChunks(audioUrl: string): Promise<ArrayBuffer[]> {
	const response = await fetch(audioUrl, { redirect: "follow" });
	if (!response.ok) {
		throw new Error(`Failed to fetch audio: ${response.status}`);
	}
	const arrayBuffer = await response.arrayBuffer();

	// Example: Split the audio into 1MB chunks.
	const chunkSize = 1024 * 1024; // 1MB
	const chunks: ArrayBuffer[] = [];
	for (let i = 0; i < arrayBuffer.byteLength; i += chunkSize) {
		const chunk = arrayBuffer.slice(i, i + chunkSize);
		chunks.push(chunk);
	}
	return chunks;
}

/**
 * Transcribes a single audio chunk using the Whisper‑large‑v3‑turbo model.
 * The function converts the audio chunk to a Base64-encoded string and
 * sends it to the model via the AI binding.
 *
 * @param chunkBuffer - The audio chunk as an ArrayBuffer.
 * @param env - The Cloudflare Worker environment, including the AI binding.
 * @returns The transcription text from the model.
 */
async function transcribeChunk(
	chunkBuffer: ArrayBuffer,
	env: Env,
): Promise<string> {
	const base64 = Buffer.from(chunkBuffer, "binary").toString("base64");
	const res = await env.AI.run("@cf/openai/whisper-large-v3-turbo", {
		audio: base64,
		// Optional parameters (uncomment and set if needed):
		// task: "transcribe",   // or "translate"
		// language: "en",
		// vad_filter: "false",
		// initial_prompt: "Provide context if needed.",
		// prefix: "Transcription:",
	});
	return res.text; // Assumes the transcription result includes a "text" property.
}

/**
 * The main fetch handler. It extracts the 'url' query parameter, fetches the audio,
 * processes it in chunks, and returns the full transcription.
 */
export default {
	async fetch(
		request: Request,
		env: Env,
		ctx: ExecutionContext,
	): Promise<Response> {
		// Extract the audio URL from the query parameters.
		const { searchParams } = new URL(request.url);
		const audioUrl = searchParams.get("url");

		if (!audioUrl) {
			return new Response("Missing 'url' query parameter", { status: 400 });
		}

		// Get the audio chunks.
		const audioChunks: ArrayBuffer[] = await getAudioChunks(audioUrl);
		let fullTranscript = "";

		// Process each chunk and build the full transcript.
		for (const chunk of audioChunks) {
			try {
				const transcript = await transcribeChunk(chunk, env);
				fullTranscript += transcript + "\n";
			} catch (error) {
				fullTranscript += "[Error transcribing chunk]\n";
			}
		}

		return new Response(fullTranscript, {
			headers: { "Content-Type": "text/plain" },
		});
	},
} satisfies ExportedHandler<Env>;

npx wrangler dev

curl "http://localhost:8787?url=https://raw.githubusercontent.com/your-username/your-repo/main/your-audio-file.mp3"

npx wrangler deploy

curl "https://<your-worker-subdomain>.workers.dev?url=https://raw.githubusercontent.com/your-username/your-repo/main/your-audio-file.mp3"

This is the transcript of the audio...