cf ai Whisper

    4

    Free speech-to-text and SRT subtitle generation using OpenAI Whisper on Cloudflare Workers AI.

    $12

    30-day refund guarantee

    Secure checkout via Stripe

    0 installsSecurity scanned

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+17 more

    See it in action

    You say

    Transcribe meeting_20231027.mp3 and generate an SRT subtitle file.

    Your agent does

    --- TRANSCRIPT (12 words) --- Hello and welcome to today's meeting. We'll be discussing the results.

    Subtitles saved: meeting_20231027.srt 1 00:00:00,000 --> 00:00:03,200 Hello and welcome to today's meeting.

    What you get

    Generate SRT subtitles for videos with precise word-level timestampsConvert voice memos and podcast episodes into searchable text transcriptsTranscribe recorded meetings without paying for expensive third-party seatsBatch process audio folders into text using Cloudflare's free AI tier

    About this skill

    What it does

    The cf-ai-whisper skill provides professional-grade audio transcription by leveraging OpenAI Whisper running on Cloudflare Workers AI. It allows developers and users to convert speech to text with high accuracy without requiring an OpenAI API key or account. The skill handles diverse audio formats and can automatically generate SRT subtitle files with word-level timestamps.

    Why use this skill

    Most transcription services are expensive or require complex local setups. This skill offers a cost-effective alternative by utilizing Cloudflare’s free tier infrastructure. Unlike basic LLM prompting, it manages the binary data handling, audio MIME-type mapping, and complex timestamp calculations required to create perfectly synced subtitles. It eliminates the frustration of manual transcription while keeping your data within the Cloudflare ecosystem you already use.

    Supported tools

    • Frameworks: Cloudflare Workers AI, OpenAI Whisper
    • Audio Formats: WAV, MP3, MP4, M4A, OGG, FLAC, WebM, and more
    • Outputs: Plain text transcripts (.txt) and SubRip Subtitle files (.srt)

    The Output

    The skill produces two primary artifacts: a clean, high-accuracy text transcript and a professionally formatted SRT file. The output includes metadata such as word count and relies on word-level timestamps to ensure subtitle synchronization is precise.

    How to install

    Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 4 months ago

    • One-time purchase, yours forever

    Listed4 months ago

    Frequently Asked Questions