Otter provides a variety of methods to transcribe existing conversation recordings.
Import an audio or video file (recommended)
If you have the audio or video file, you can import (upload) directly to Otter from your computer or mobile device. When you import a file, Otter will process the audio speech and create a transcription. Learn more about importing a file.
Transcribe the conversation playback
If you don't have access to the recorded audio or video file, you can transcribe the conversation by playing it back using Otter.
Recording through Otter Record audio playback through our desktop, web, or mobile app
We recommend downloading our desktop app to transcribe audio playback. The desktop app allows you to wear headphones and still record the playback audio.
- Play the conversation audio.
- Begin recording the conversation in the Otter desktop, web, or mobile app.
When using the Otter mobile app, place your device next to your computer's speaker, and refrain from moving or touching the device to avoid any unnecessary background noise that can affect the transcription accuracy
Record through the Otter Chrome Extension Record your Chrome tab audio playback with our Otter extension
If you want to transcribe online videos or audio playing in your browser, we recommend using the Otter Chrome Extension. Unlike manual recording, the Chrome Extension can capture the browser tab’s internal audio, allowing Otter to transcribe playback without relying on your microphone.
This means you can wear headphones while recording, and Otter will still capture the audio playing in the browser tab.
FAQs
Will speaker tagging automatically apply to imported or newly transcribed recordings?
Yes, if Otter has already learned that speaker. If a speaker has been tagged previously, Otter uses their existing speaker profile to automatically identify and label them in future recordings and transcriptions.
If Otter encounters a new speaker or someone who hasn’t been tagged before, you’ll need to manually assign their speaker name after the transcription finishes processing. Once tagged, Otter creates a speaker profile and can automatically identify that speaker in future recordings.
Feedback
0 comments
Article is closed for comments.