Google Gemini Adds Audio Uploads

Google’s Gemini app now allows users to upload audio files, fulfilling one of the platform’s most requested features. Free accounts can upload up to 10 minutes per prompt, while paid plans extend this limit to three hours.

Users can submit up to 10 audio files per prompt, making it easier to convert podcasts, interviews, or calls into notes, quotes, or draft content. For marketing and content teams, this update streamlines the process, allowing recordings to be analysed, summarised, and repurposed directly within Gemini without switching between tools.

Josh Woodward, VP at Google Labs and Gemini, shared the update on X, highlighting that the app now supports all file types, including the highly anticipated audio upload feature.

What’s New

Gemini now supports audio file uploads within the same multi-file workflow previously available for documents and images.

Users can attach up to 10 files per prompt, and ZIP archives are also accepted. This makes it easy to upload multiple recordings at once, such as raw audio tracks or several takes from an interview.

Limits

Free plan: total audio length up to 10 minutes per prompt; up to 5 prompts per day.
AI Pro and AI Ultra: total audio length up to 3 hours per prompt.
Per prompt: up to 10 files across supported formats. Details are listed in Google’s Help Center.

Why This Matters

For teams handling podcasts, webinars, interviews, or customer calls, this update removes the need for a separate transcription step.

You can upload an entire recording and immediately generate show notes, key quotes, or a working draft in one place. It also benefits teams with frequent meetings, allowing strategy sessions to be converted into action items and summaries without switching between tools.

Agencies and networks can batch multiple episodes or takes into a single prompt, streamlining weekly workflows.

The key advantage is fewer handoffs: audio is uploaded once, and the system produces the outlines, summaries, and excerpts you need, all within the same platform you already use for text prompts.

Quick Tip

You can include your audio along with any relevant context within the same prompt. Providing this background helps Gemini generate clearer summaries and more precise excerpts.

For those using the free plan, remember there’s a 10-minute limit per prompt, so longer recordings are better suited for the AI Pro or Ultra tiers.

Looking Ahead

You can include your audio along with any relevant context within the same prompt. Providing this background helps Gemini generate clearer summaries and more precise excerpts.

For those using the free plan, remember there’s a 10-minute limit per prompt, so longer recordings are better suited for the AI Pro or Ultra tiers.