How to Use WhisperAI

Complete step-by-step guide to transcribing audio with WhisperAI. Learn both live recording and file upload methods.

5 min read

Beginner Friendly

Step-by-Step Guide

Quick Start Overview

Live Recording

Record directly from your microphone or system audio and get instant transcription.

File Upload

Upload existing audio files (MP3, M4A, WAV, etc.) up to 5GB for transcription.

Live Recording Tutorial

Access the Dashboard

If you don't have an account yet, sign up here and choose your plan.

Choose Your Audio Source

Click "Record Live" on your dashboard and select your audio source:

Microphone Only

Record your voice directly.

System Audio Only

Capture computer audio playback.

Both Sources

Record mic + system audio together.

System Audio Use Cases

• Video Meetings: Zoom, Teams, Google Meet
• Online Lectures: Educational content, webinars
• YouTube Videos: Transcribe video content
• Podcasts: Convert streaming audio to text

Grant Browser Permissions

Your browser will ask for permission to access your microphone and/or system audio.

For System Audio Recording:

Click "Allow" when prompted for screen sharing permission.
Select "Entire Screen" or a specific window/tab.
Check the "Share audio" checkbox (this is required).
Click "Share" to begin.

If you block permissions by mistake, look for the camera or microphone icon in your browser's address bar to re-enable them.

Configure Recording Settings

Before you begin, you can customize your session:

Language: Choose your preferred language, or leave it on "Auto-detect".
Audio Source: Verify your selected audio inputs.
Title: You can set a custom title after you finish, before saving.

Record Your Audio

Click the red record button to start recording.

While Recording

•A live waveform visualizes your audio input in real time.
•A timer displays your current recording duration.
•Toggle Live Transcription and Live Translation to see text appear as you speak.

Recording Controls

•Pause / Resume: Temporarily pause and continue recording.
•Stop: End the recording and move to the review step.
•Discard: Delete the current recording and start over.

Safari & iOS Users: WhisperAI automatically switches to a raw-PCM streaming pipeline on Safari. This uploads audio in small chunks continuously, supporting multi-hour sessions without capping your recording length.

🎙️ Best Practices for Accuracy

Speak clearly, minimize background noise, and ensure your microphone is positioned 6-12 inches from your mouth for the best transcription results.

Stop, Review & Save

When you're finished recording, follow these steps:

Click the stop button to end your recording.
Review the recording card: play it back, enter a descriptive title, and adjust language or speaker settings if necessary.
Click Save to confirm.

Automatic Processing: As soon as you click Save, WhisperAI kicks off transcription in the background. There's no separate upload button. You can navigate away to other pages while it processes.

View Your Transcription

After saving, your recording workflow is complete.

The file begins transcription processing immediately.
It will display a "Processing" status in your Recent Recordings list.
Once finished, you can view the transcribed text, speaker labels, and an AI-generated summary.

Note: Processing time depends on length. Most recordings under 10 minutes process within 30-60 seconds.

Working with Your Transcriptions

Review and Summarize

Once processing completes, your transcription view includes:

Synchronized TextFull transcribed text that follows along with audio playback.

Speaker DiarizationSpeakers are automatically detected and labeled. You can tell WhisperAI to expect anywhere from 1 to 10 speakers before transcribing.

AI SummaryAn auto-generated breakdown featuring key points, action items, and topic highlights.

Custom Prompts: Before transcribing, add a custom prompt or list of important terms (names, acronyms, jargon). This guides the engine's vocabulary, which is especially useful for technical, medical, or legal recordings.

Edit and Enhance

Use our built-in editing suite to polish your document:

Edit transcription text directly to correct any minor mistakes.
Add formatting and structure for readability.
Translate the text into dozens of supported languages.
Re-generate AI summaries if you edit the source text.

Note: All edits auto-save as you type. Your original transcription is safely preserved.

Export Your Work

Download your finished transcription in the format you need:

TXTPlain text

PDFDocument

SRT / VTTSubtitles

JSONStructured data