Is there a limit on episode length?

No. Long episodes simply take longer to process — roughly a third to half of the episode duration on a typical laptop with the Accurate model.

Can I publish the transcript on my site?

Yes, it is your content. Published transcripts also help people find the episode, since search engines and AI assistants can read text but not audio.

How accurate is it with two hosts and a guest?

Word accuracy is good with clear recordings; what it will not do is label who spoke. Expect a pass to add names and fix technical terms.

Transcribe a Podcast to Text — Free, Private, In-Browser

Turn podcast episodes into transcripts and show notes. 100% free, no per-minute billing, no upload — runs entirely in your browser.

Model

Spoken

Output

Timestamps [0:05]

🌍 The spoken language is detected automatically and the transcript comes out in that same language. Set it manually above if your audio is hard to hear, and use Output to translate into English.

⬇️ One-time download: 104 MB (Accurate model 73 MB + 31 MB audio engine, shared with the video tools) — only the first time: it stays saved in your browser, so next time it starts right away. (Translating or switching model needs its own file; a browser can clear this cache if storage runs very low.) Processing takes about 4-8 min per 10 minutes of audio on a typical laptop.

What exactly is downloaded — and is it safe?

• The speech model is OpenAI's Whisper, open source, converted to run in browsers. The audio engine is FFmpeg, the open-source tool behind most video software.
• They come from Hugging Face and unpkg — public repositories used by researchers and developers worldwide, not from us.
• They are not programs. Nothing is installed, no permission is asked, and your browser keeps them in its own cache exactly like it keeps a website's images.
• They can't read your files or touch anything outside this page. Remove them any time by clearing this site's data in your browser.
• Your audio never goes the other way: this site has no server receiving files.

Drop your video or audio here or click to choose

transcribed on your device by OpenAI's Whisper — your recording is not uploaded

ℹ️ Use a recording on your device that you own or have permission to process. This tool cannot fetch YouTube or social video links. Start with a short clip. Larger models can improve accuracy but require more memory and download data. Processing time varies by device, model and recording length. Always review the result.

A transcript is the cheapest growth lever a podcast has: it makes an episode searchable, gives you the raw material for show notes and quotes, and turns an hour of audio into a page that search engines and AI assistants can actually read. The reason most independent shows skip it is pricing — transcription is usually billed per minute, and a weekly show is several hours a month.

This page removes that cost entirely by running OpenAI's Whisper in your browser. There is no per-minute charge and no cap: an entire back catalogue costs nothing but your computer's time. Export as plain text for show notes, or as .SRT if you publish video versions and want captions that match.

More sizes & options

Frequently asked questions

Is there a limit on episode length?: No. Long episodes simply take longer to process — roughly a third to half of the episode duration on a typical laptop with the Accurate model.
Can I publish the transcript on my site?: Yes, it is your content. Published transcripts also help people find the episode, since search engines and AI assistants can read text but not audio.
How accurate is it with two hosts and a guest?: Word accuracy is good with clear recordings; what it will not do is label who spoke. Expect a pass to add names and fix technical terms.

Guides

Related tools

🔒 Private mode (the default): your recording never leaves your device. Instant mode is optional, you switch it on yourself, and it sends the audio to the browser's speech service.