Under the Hood

What happens between your recording and your brief.

Two stages. One result.

Every recording submitted to Trootone passes through two stages before your brief arrives. The first stage captures every word spoken. The second stage reads what was said and turns it into something you can act on. Both stages run automatically, in sequence, and complete within minutes regardless of how long your recording is.

Stage one: listening

Your recording is processed to extract every word, speaker, and moment that matters.

Stage two: intelligence

The transcript is passed to a language intelligence system that reads it the way a skilled professional would. It identifies what was decided, what needs to happen, who is responsible, what was flagged as a concern, and what deadlines were mentioned. It then structures all of that into a clean, readable brief in the format you selected. This system does not guess or invent. If something was not said in your meeting, it will not appear in your brief. If a name or technical term appears unclear in the transcript, it is flagged for your review rather than assumed.

Export and delivery

Once your brief is generated Trootone can package it in eight different formats depending on what you need: PDF, DOCX, SRT, Markdown, RTF, HTML, TXT, and CSV. PDF and DOCX are professional documents ready to share. SRT is for video producers who need timestamped subtitles. Markdown is for knowledge workers in tools like Notion and Obsidian. RTF opens in virtually every word processor. HTML is for anyone embedding content into a website or email. TXT is plain text for any tool. CSV is for data teams who want to pull figures directly into spreadsheets. All formats are generated from the same brief text, which means the content is identical across every format. Only the packaging changes. Export files are deleted from our servers within two hours of generation.

Why we do not name our technology partners

We evaluate the tools that power Trootone on an ongoing basis and update them when better options become available. Naming specific vendors would create the impression that our output quality is fixed to one provider. It is not. Trootone's quality commitment is to the brief you receive, not to any particular technology stack behind it.

What we do not share

Your audio, transcript, and brief content are never shared with any third party beyond the two processing stages described above. We do not use your content to improve any model. We do not retain recordings after brief generation. The infrastructure that runs Trootone is built with security as a baseline, not an afterthought.

Optional conversation intelligence

When the Conversation Intelligence add-on is selected, Trootone uses a second specialised system that adds speaker diarisation, sentiment analysis, and automatic chapter detection. Speaker diarisation identifies who said what throughout the recording so the brief can attribute statements, decisions, and action items to specific participants. Sentiment analysis measures the emotional tone of each speaker across the conversation. Automatic chapters divide longer recordings into named topic sections each with its own summary. This enriched transcript is then passed to the language intelligence system, producing a more detailed and attributed brief than standard brief generation alone.