Y/Yangopen
← Products

Audio to text

Drop audio or video here MP3 / WAV / M4A / OGG / WebM / MP4 · max 500 MB
0 words

How to transcribe audio to text

  1. 1. Paste a Groq API key

    Get a key at console.groq.com (Get free key →) and paste it in Groq API Key. You need it for files, not for live dictation.

  2. 2. Select the language

    Select the Spoken Language before you add the file, or keep Auto-detect language.

  3. 3. Add audio or video

    Drop an MP3, WAV, M4A, OGG, WebM or MP4 up to 500 MB on the box, or click it to select one. Transcription starts at once, and the text shows part by part.

  4. 4. Select the format and download

    Select Plain text, Subtitles (.srt) or WebVTT (.vtt) in Output Format. Then click Copy text or Download.

Frequently asked questions

Where does my audio go?

A file goes from your browser directly to Groq, which runs the Whisper AI model with your own API key. It does not go through our servers. Live dictation uses the speech service of your browser: Chrome sends your voice to Google, and Edge sends it to Microsoft.

Is Audio to text free?

Yangopen does not charge for it, and you need no account. File transcription runs on your own Groq account, so the terms and limits of Groq apply. When Groq asks you to wait, the tool waits and then continues by itself.

Do I need a Groq API key?

Only to transcribe files. You can get a key at console.groq.com. The tool sends the key only to Groq, with your audio, and never to our servers. Live dictation needs no key.

Can I make SRT subtitles from a video?

Yes. Add an MP4 or WebM video, then select Subtitles (.srt) or WebVTT (.vtt) in Output Format. Each line gets its start and end time. You can change the format after transcription, without a new run.

Which languages does it support?

Auto-detect language, or 19 languages you can select, such as Vietnamese, English, Chinese, Japanese, Korean, Thai and Indonesian. For a file, Auto-detect lets Whisper find the language. For live dictation, select the language you will speak.

Which browsers support live dictation?

Browsers with built-in speech recognition, such as Chrome and Edge. In other browsers, the tool tells you to use Chrome or Edge. Allow the microphone when the browser asks.

How long can a recording be?

A file can be up to 500 MB. Your browser decodes the full recording in memory, then cuts it into 12-minute parts that go to Groq one by one. A very long recording can fail on a device with little memory.