How to Upload Files to Speak AI
Upload methods
From your dashboard, click Upload (or use the quick actions panel). You have several options:
Upload a file from your computer
Click File and select an audio or video file from your computer
Choose the destination folder (optional)
Click Upload
Supported formats include MP3, MP4, WAV, M4A, FLAC, MOV, AVI, and more. See our full format list.
Upload from a URL
Click URL
Paste a direct link to an audio or video file
Click Import
This works with any publicly accessible media URL.
Upload a YouTube video
Click URL
Paste a YouTube video URL
Speak AI extracts the audio automatically
Record directly in the app
Click Record
Allow microphone access
Record your audio and click Stop when done
Name your recording and save it
Bulk upload via CSV
For uploading many files at once, prepare a CSV with columns for URL, Name, and Folder, then use the CSV upload option. Great for migrating large libraries.
What happens after upload
Transcription: Speak AI automatically transcribes your audio in 70+ languages
Speaker identification: Speakers are detected and labeled
Analysis: Keywords, sentiment, entities, and topics are extracted
Notification: You receive a notification when processing is complete
Most files under 30 minutes are ready within a few minutes. Longer files take proportionally longer.
Tips
Organize with folders: Select a destination folder during upload to keep things organized from the start
Name your files: Give descriptive names so they're easy to find later
Check your balance: Upload uses your transcription minutes. Check your remaining balance in your dashboard.
Need help? Send us a message or check our troubleshooting guide if uploads fail.