Speech to Text Transcriber

Upload an audio file and receive a transcript using Workers AI Whisper (@cf/openai/whisper-large-v3-turbo). Validates file size and content type before calling the model.

FeaturesCopy Anchor Link

• POST /transcribe - Multipart upload with field audio
• Whisper model - @cf/openai/whisper-large-v3-turbo
• Validation - Max 2 MB, audio/* types only
• Timing - Returns durationMs for the transcription call

API ReferenceCopy Anchor Link

POST /transcribeCopy Anchor Link

Transcribe an uploaded audio file.

audio file (required, multipart)

Audio file (max 2 MB). Accepted types include audio/mpeg, audio/wav, audio/webm, audio/ogg, and other audio/* MIME types.

Example RequestCopy Anchor Link

curl -X POST "https://your-worker.workers.dev/transcribe" \
  -F "audio=@sample.mp3"

Success ResponseCopy Anchor Link

{
  "text": "Hello, this is a test recording.",
  "language": "en",
  "durationMs": 842
}

Error CodesCopy Anchor Link

• 400 - Missing or invalid audio (INVALID_AUDIO)
• 502 - Transcription failed or empty result (TRANSCRIBE_ERROR)

Use CasesCopy Anchor Link

• Add speech-to-text to edge apps without external API keys
• Prototype voice note or meeting transcription workflows
• Learn Workers AI audio model integration patterns

LimitationsCopy Anchor Link

• Max upload size 2 MB per request (Whisper model limits apply)
• No chunking for long recordings; split large files client-side
• Requires Workers AI enabled on your Cloudflare account

Use in your projectCopy Anchor Link

import { ALLOWED_AUDIO_TYPES, MAX_AUDIO_BYTES } from "../constants/defaults";export async function validateAudioFile(  file: File | null): Promise<{ buffer: ArrayBuffer; type: string } | null> {  if (!file || !(file instanceof File)) return null;  if (file.size === 0 || file.size > MAX_AUDIO_BYTES) return null;  const type = (file.type || "audio/mpeg").toLowerCase();  const isAudio =    type.startsWith("audio/") ||    ALLOWED_AUDIO_TYPES.includes(type as (typeof ALLOWED_AUDIO_TYPES)[number]);  if (!isAudio) return null;  const buffer = await file.arrayBuffer();  return { buffer, type: file.type || "audio/mpeg" };}export function toBase64Audio(buffer: ArrayBuffer): string {  const bytes = new Uint8Array(buffer);  let binary = "";  for (let i = 0; i < bytes.length; i++) {    binary += String.fromCharCode(bytes[i]);  }  return btoa(binary);}

DeploymentCopy Anchor Link

curl -X POST "https://your-worker.workers.dev/transcribe" -F "audio=@sample.mp3"

Local DevelopmentCopy Anchor Link

cd apps/experiments/speech-to-text-transcriber
npm install
npm run dev

ConfigurationCopy Anchor Link

Cloudflare Features UsedCopy Anchor Link

• Workers - Edge compute runtime
• Workers AI - Whisper speech-to-text