Getting Started

No — you can transcribe your first audio file without creating an account. Just drop a file on the homepage and we'll generate a preview transcription right there so you can see how it works.

When you're ready to save transcriptions, run longer files, or use AI chat and summaries, sign up for free. The Free plan gives you 60 minutes/month with no credit card required, and any preview you uploaded before signing up gets linked to your new account automatically.

Click Sign up, enter your email and a password, and you're in. There's no credit card to enter — the Free plan is automatic and gives you 60 minutes/month.

We'll send a confirmation email to verify your address, but you can start transcribing right away while you're signed in. If you uploaded an audio file as a guest before signing up, that transcription is linked to your account automatically so it's waiting in your dashboard.

We accept the most common audio and video containers: .mp3, .wav, .ogg, .m4a, .flac, .webm, and .mp4. If your file plays in a normal media player, it almost certainly works.

For best results, use a clear recording with minimal background noise — see What audio quality gives the best results? for tips. If you have a format we don't list, convert it to .mp3 or .wav first with a free tool like Audacity or ffmpeg.

The maximum file size per upload is 1GB. Files larger than 25MB are automatically split into smaller chunks behind the scenes — you don't need to do anything.

We support .mp3, .wav, .ogg, .m4a, .flac, .webm, and .mp4. If your file is larger than 1GB, trim it into shorter segments first, or compress it to a lower bitrate (128 kbps mono is plenty for spoken-word audio).

On the upload form there's a Language dropdown next to the file picker. Pick the language your audio is in, or leave it on Auto and we'll detect it for you.

We support 99 languages — see What languages can I transcribe? for the full list. Setting the language explicitly usually gives slightly better accuracy than auto-detect, especially for short clips or audio with multiple languages mixed in.

We upload your audio securely, queue it for transcription, and start processing right away. You'll see a progress bar update in real time — most files are done in under a minute.

When it's ready, you'll see the full transcribed text on screen. From there you can copy it, download it as .txt, .srt, .doc, or .pdf, ask questions about it with AI chat, or generate an AI summary. If you're signed in, the transcription is saved to your dashboard.

Most files are transcribed in seconds to a couple of minutes. A typical 10-minute audio file is usually done in under 30 seconds.

Speed depends on file length, audio quality, and whether you enabled speaker identification (which adds a bit of processing time). Your dashboard polls in real time, so you don't need to refresh — when the result is ready, it appears automatically.

The homepage upload zone is designed for first-time visitors — it works without an account and shows a preview transcription right on the page so you can try us in seconds.

The dashboard is for signed-in users and adds everything you'd expect: a list of all your past transcriptions, search and filters, downloads in multiple formats, AI chat per transcription, AI summaries, and your monthly usage card. Same transcription engine — just more tools around it.

Yes — SoundScript.AI works in any modern mobile browser (Safari on iOS, Chrome on Android, etc.). The interface adapts to small screens and you can upload directly from your phone's files, voice memos, or recording apps.

If you record voice memos on iPhone, share them to "Files" first, then upload from there. On Android, most recorders save to your Downloads folder. We don't have a dedicated app — the web version handles everything you need.