Gemini alternative

Gemini audio transcription alternative: Scriptorium vs Gemini

Google now offers transcription in two places: the Gemini app, where you can upload audio, and a dedicated model, Gemini 3.5 Transcribe, for developers. Both are real options for a short clip or a pipeline. They give you text, not a subtitle file, and the pages we read set tight free limits for the app. Scriptorium is a web page where you upload a file and download a transcript or SRT. Read on 2026-10-27, from Google's own pages.

Updated 2026-10-27

Where Gemini is the better choice

The Gemini app's help page sets total audio length at up to 10 minutes on the free tier and up to 3 hours with Google AI Pro or Ultra.
Gemini 3.5 Transcribe is listed free of charge on the API free tier, with word timestamps, a custom vocabulary of up to 1,000 terms and files up to 1 hour per request (30 minutes with speakers or word timestamps), per its developer docs.
It is built for pipelines: a developer can call it from code and send the text on to summarising or analysis in the same ecosystem.

Where Scriptorium fits better

A finished web page for the job: upload, read, correct, export. No API key, and no account for a first file.
SRT and VTT subtitle files from the same transcript; the Google pages we read mention no subtitle file formats.
Arabic as an ordinary language choice, with our own measured error rate published; Gemini 3.5 Transcribe's docs list Arabic (Egypt) only, among 85+ locales.

Gemini and Scriptorium side by side

Topic	Gemini	Scriptorium
Free route	App: total audio length up to 10 minutes without a paid Google AI plan. API: Gemini 3.5 Transcribe is free of charge on the free tier (rate limits are shown in AI Studio, not on the page read)	One file up to 15 minutes and 25 MB, 3 tries a day, no account
Account for the free route	App: signed in to Gemini Apps (its help page). API: a Google developer key	No for the first file; a free account adds a saved library
Languages	Gemini 3.5 Transcribe: over 85 (Google's blog); the app help page lists none	33 plus automatic detection
Exports	Text and API data; no SRT, VTT or DOCX is mentioned on the pages read	TXT, timestamped TXT, SRT, VTT, Markdown, JSON and CSV
Speaker identification	Up to 3 speakers per Google's blog and up to 8 per its developer docs (they disagree); beyond 3 is called experimental	Optional speaker labels, up to 8 speakers
Meeting bot	No bot described	No bot: you upload the recording after the call
Entry paid price	API: about $0.003 a minute of audio input plus text output (its pricing page); consumer Google AI plan prices were not read	Pro $9.99 a month (600 minutes), Pro+ $19.99 a month (2500 minutes)
Max file length	App: 10 minutes free, 3 hours on Pro or Ultra. Gemini 3.5 Transcribe: 1 hour per request, 30 minutes with speaker labels or word timestamps	15 minutes and 25 MB on the preview; account limits on the pricing page
Accepts links	Check their site	No: files only

Checked on 2026-10-27 from the vendor's own pages listed below. Prices and limits change; confirm on their site before you buy. A cell that says "Check their site" means the page did not state it, was unreadable to us, or contradicted itself, and we chose not to guess.

Which should you pick?

Pick Gemini if You are a developer, or you already use Gemini and want text from a short clip, and plain text output is enough.
Pick Scriptorium if You want a browser tool with timestamps and SRT/VTT export, no developer key and no account for a first file.

Scriptorium's transcripts are automatic and make mistakes; read them against the audio. The free preview is on the home page, and the pricing page lists plans.

Sources

Questions

Can Gemini transcribe an audio file?

Google's help page for the Gemini app sets audio limits (10 minutes in total, 3 hours on Google AI Pro or Ultra; the page does not use the word free) but does not mention transcripts. Separately, Google offers Gemini 3.5 Transcribe, a dedicated model for developers. Checked 2026-10-27.

Is Gemini 3.5 Transcribe free?

Google's API pricing page lists it as free of charge on the free tier; paid input is priced per minute of audio. Its blog calls it a public preview while its models page says stable, so check Google's pages.

Does Gemini give me an SRT file?

The pages we read mention no subtitle formats. Scriptorium exports SRT and VTT.

Is it free?

Yes — one file up to 15 minutes and 25 MB with no account, up to 3 tries a day. A free account keeps your transcripts in a library and lifts the guest limits; the current limits and paid plans are on the pricing page.

Try it with your own file

Upload a recording and read the transcript.

Transcribe free — no sign-up Create free account