How to transcribe audio for free without uploading it: an Otter alternative

To transcribe audio for free without uploading it, drop the recording into Dictate. It runs the Whisper speech model in your browser, on your own device, and gives you a transcript with timestamps that you can download as plain text or as .srt subtitles. There are no minute limits and no account, and the audio never leaves your device.

Otter's free plan is reported at 300 minutes a month, with 30 minutes per conversation and few file imports, and Pro is about $8 to $17 a month, as reported in 2026. Otter also uploads your recordings to transcribe them.

Step by step

1. Open Dictate in a modern browser on your computer or phone. The first time, it downloads the speech model and keeps it, so later visits are quicker and work offline.
2. Choose Fast or Accurate. Fast suits clear recordings and most devices. Accurate is slower and makes fewer mistakes.
3. Drop in an audio or video file: a voice memo, an interview, a lecture. The file stays on your device.
4. Wait while it works. Dictate shows how far it has got. Keep the tab open.
5. Read the transcript, with a timestamp for each part.
6. Download it as .txt for reading and editing, or as .srt for subtitles.

How long does it take?

It depends on your device and the length of the recording. Dictate uses your device's graphics chip when the browser allows it, which is faster, and the main processor otherwise. A recent laptop is the most comfortable place for long recordings. An older phone will be slow on a long file. Try Fast first on a long recording, and switch to Accurate if the result needs it.

Tips for a better transcript

• Start with clean audio. A microphone close to the speaker helps more than any setting.
• One language per file gives the best results.
• Check names, numbers and jargon. Speech models guess at words they have rarely heard.
• Use Accurate for anything you will publish or quote.

Using the subtitles

An .srt file is the standard subtitle format. Most video editors and video sites accept it: add it next to your video, and the captions appear in time with the speech. Read it through first and fix any misheard words, since captions get read closely.

What Dictate does not do

Otter and other paid services do more, and it helps to know where the line is:

• No speaker labels. The transcript does not say who said what.
• No summaries or action items.
• No meeting bot. Dictate does not join your calls. Record the call, with permission, then drop the file in.
• No shared workspace. Transcripts stay on your device until you download and share them.

If you need those, a paid service like Otter is built for it. If you need a private transcript of a file, Dictate does that for free.

Other free ways to transcribe privately

• Whisper desktop apps. Buzz is open source and runs Whisper on your computer. MacWhisper has a free version for Mac. Desktop apps can run larger Whisper models than a browser can, if your computer is up to it.
• Your phone's recorder. Some phones transcribe recordings on the device in their built-in recorder app. Check yours.
• whisper.cpp. For people comfortable in a terminal, it runs Whisper models quickly on a laptop.

A note on consent

Before you record a conversation, ask the people in it. In many places, recording someone without their consent is against the law, and it is always polite to ask.

If you want to dictate rather than transcribe a file, see free voice dictation that stays on your device.

Questions

How can I transcribe audio for free?

Drop the recording into OpenApps Dictate. It transcribes audio and video files in your browser, on your own device, with timestamps, and lets you download the transcript as .txt or as .srt subtitles. There is no account and no minute limit.

Is my audio uploaded when I transcribe with Dictate?

No. OpenApps Dictate runs the Whisper speech model inside your browser. The recording and the transcript stay on your device and are never sent to a server.

Is there a limit on how many minutes I can transcribe?

No. OpenApps Dictate has no word or minute limits, because your own device does the work. Long recordings simply take longer on slower devices.

Can Dictate make subtitles for a video?

Yes. OpenApps Dictate can transcribe a video file and export the result as an .srt subtitle file, which most video editors and video sites accept.

Does Dictate identify different speakers?

No. OpenApps Dictate gives you the words with timestamps, but it does not label who said what. Paid services like Otter offer speaker labels and meeting summaries.