Cloudflare Docs
Workers AI
Cloudflare Docs
Workers AI
GitHub icon
Visit Workers AI on GitHub
Set theme to dark (⇧+D)
  1. Products
  2. Workers AI
  3. Models
  4. Speech to text

Speech to text

Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web.

​​ Examples 


import { Ai } from "@cloudflare/ai";



export interface Env {
	AI: any;

}



export default {
	async fetch(request: Request, env: Env) {
    const res: any = await fetch("https://github.com/Azure-Samples/cognitive-services-speech-sdk/raw/master/samples/cpp/windows/console/samples/enrollment_audio_katie.wav");
    const blob = await res.arrayBuffer();


    const ai = new Ai(env.AI);
    const input = {
      audio: [...new Uint8Array(blob)],
    };


    const response = await ai.run("@cf/openai/whisper", input);


    return new Response(JSON.stringify({ input: { audio: [] }, response }));
	}

};


$ curl https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/openai/whisper \
    -X POST \
    -H "Authorization: Bearer {API_TOKEN}" \
    --data-binary @talking-llama.mp3

​​ API schema

The following schema is based on JSON Schema


{
    "task": "speech-recognition",
    "tsClass": "AiSpeechRecognition",
    "jsonSchema": {
        "input": {
            "type": "object",
            "properties": {
                "audio": {
                    "type": "string",
                    "format": "binary"
                }
            },
            "required": ["audio"]
        },
        "output": {
            "type": "object",
            "properties": {
                "text": {
                    "type": "string"
                }
            }
        }
    }

}