What are the audio upload and file requirements?

ContentPod supports all common audio formats:

• MP3 (.mp3)
• WAV (.wav)
• M4A (.m4a)
• FLAC (.flac)
• OGG (.ogg)
• AAC (.aac)

For best results, we recommend MP3 (320 kbps) or WAV files.

Yes! Upload video files and ContentPod extracts the audio automatically:

• MP4 (.mp4)
• MOV (.mov)
• WebM (.webm)

The Video Clip Creator tool also supports uploading video for AI-powered clip extraction (Pro and Team plans).

File processing: Whisper AI handles files up to 25 MB directly. Larger files are processed via Gemini, which supports up to 500 MB.

Processing time depends on audio length and file size:

• Short files (under 5 minutes): 30–60 seconds
• Medium files (5–15 minutes): 1–3 minutes
• Longer files (15–30 minutes): 2–5 minutes

You can continue using ContentPod while processing completes.

For longer content, use multi-part interviews — create several focused interviews on the same topic.

Yes! ContentPod has built-in voice recording for interviews:

• Click the microphone icon during any interview
• Grant browser microphone access (one-time)
• Speak your answers naturally
• Audio is transcribed in real time

• Use a quiet environment with minimal background noise
• Speak clearly at a natural pace
• Use headphones to reduce echo
• A USB microphone improves quality but isn't required — built-in laptop mics work fine

Files are stored securely on Cloudflare R2 cloud storage:

• Encrypted in transit (TLS)
• Accessible only to you (and team members on Team plan)
• Download or delete anytime from your dashboard

Learn more: Read our AI Interview guide for tips on getting the best interview results.