Interviews and podcasts
Get a searchable transcript to quote from, write show notes with, or publish next to the episode.
Upload an audio file and get an editable transcript with timestamps. Copy the text or download it as TXT, SRT or VTT.
Choose an MP3, WAV, M4A, AAC, OGG or FLAC file up to 60 minutes long. Video files work too.
Leave the language on automatic detection or pick it yourself. The button shows the price before you start: 2 credits per started minute.
Fix any wrong words on the page, then copy the text or download a TXT, SRT or VTT file.
Get a searchable transcript to quote from, write show notes with, or publish next to the episode.
Turn a recorded meeting or a long voice note into text you can skim, search and share.
Keep a written copy of a class, so you can find the part you need without listening again.
Pick the plan that matches your pace
Subscribers get +20% extra credits at the same price
≈ 18 videos5s · 480p each
Subscribers receive: 1,080
≈ 38 videos5s · 480p each
Subscribers receive: 2,280
≈ 110 videos5s · 480p each
Subscribers receive: 6,600
≈ 240 videos5s · 480p each
Subscribers receive: 14,400
Subscriptions renew automatically at the price shown until you cancel, and we'll tell you before any price change. Cancel anytime in Settings → Billing; you keep access until the paid period ends. Credit packs are one-time and expire 180 days after grant. Prices include any tax collected at checkout. Refunds & Billing · Terms · Privacy Policy · Contact Us · Pricing
aiMakeVideo is an independent AI video platform and is not affiliated with the model providers.
2 credits per started minute, so a 30-minute recording costs 60 credits. Signup credits, where offered, cover a short clip. If a transcription fails, the credits go back to your account automatically.
MP3, WAV, M4A, AAC, OGG, FLAC and other common formats, up to 60 minutes per file. Split a longer recording before you upload it.
Yes. Every line in the editor shows when it starts, and SRT and VTT downloads carry the full timing. The TXT download is plain text.
The Whisper speech recognition model detects the spoken language automatically and covers nearly 100 languages. You can also pick one of 19 common languages yourself. The transcript stays in the spoken language: it is not translated.
An audio copy is uploaded to our storage and to our speech recognition provider to create the transcript. Your transcripts appear only in your account.