Google’s Gemini app now accepts audio file uploads, answering what the corporate acknowledges was its most requested function.
For entrepreneurs and content material groups, it means you possibly can push recordings straight into Gemini for evaluation, summaries, and repurposed content material with out leaping between instruments.
Josh Woodward, VP at Google Labs and Gemini, introduced the change on X:
“Now you can add any file to @GeminiApp. Together with the #1 request: audio recordsdata at the moment are supported!”
What’s New
Gemini can now ingest audio recordsdata in the identical multi-file workflow you already use for paperwork and pictures.
You possibly can connect as much as 10 recordsdata per immediate, and recordsdata inside ZIP archives are supported, which helps while you need to add uncooked tracks or a number of interview takes collectively.
Limits
- Free plan: complete audio size as much as 10 minutes per immediate; as much as 5 prompts per day.
- AI Professional and AI Extremely: complete audio size as much as 3 hours per immediate.
- Per immediate: as much as 10 recordsdata throughout supported codecs. Particulars are listed in Google’s Assist Middle.
Why This Issues
In case your workforce works with podcasts, webinars, interviews, or buyer calls, this closes a spot that always compelled a separate transcription step.
You possibly can add a full interview and switch it into present notes, pull quotes, or a working draft in a single place. It additionally helps meeting-heavy groups: a recorded technique session can change into motion objects and a short with out exporting to a different software first.
For companies and networks, batching a number of episodes or takes into one immediate reduces friction in weekly workflows.
The sensible win is fewer handoffs: supply audio goes in, and the outlines, summaries, and excerpts you want come out. Inside the identical system you already use for textual content prompting.
Fast Tip
Add your audio along with any supporting context in the identical immediate. That provides Gemini the grounding it wants to supply cleaner summaries and extra correct excerpts.
In the event you’re testing on the free tier, plan across the 10-minute ceiling; longer content material is greatest on AI Professional or Extremely.
Trying Forward
Google’s limits pages do change, so regulate complete size, file-count guidelines, and any new guardrails that have an effect on longer recordings or bigger groups. Additionally look ahead to deeper Workspace tie-ins (for instance, simpler handoffs from Meet recordings) that might streamline getting audio into Gemini with out handbook uploads.
Featured Picture: Picture Company/Shutterstock
