Privacy-first conversation analysis

Every conversation has more to tell.

Drop in an interview, a meeting, a lecture — Debrief transcribes it on your own machine, works out who said what from the actual audio, and turns the transcript into analysis you can question. Nothing is uploaded unless you choose a cloud AI.

Local-first. Your recordings, transcripts, and speaker data stay on this device.

From recording to insight

Transcribe

Audio in, text out

Drag in audio or video — MP3, WAV, MP4, MOV, and more. Whisper runs locally in a bundled sidecar, with FFmpeg included, so it just works offline.

Identify

Who said what

Speaker diarisation from the actual audio — pyannote listens to voices, not text, so speakers are separated reliably. Name them once and the transcript follows.

Analyse

Beyond the words

Summaries, themes, tone, and a conversation-quality score across clarity, depth, balance, and pace — with concrete strengths and things to work on.

Ask

Chat with your library

Question a single transcript, a project, or your whole library. Retrieval-backed chat finds the moments that matter and answers with the evidence.

Bring your own AI

Fully local, by default

Point Debrief at Ollama and everything — audio, transcript, analysis, chat — stays on your machine. Transcription and speaker identification are local no matter what.

Or any major provider

Anthropic Claude, OpenAI, Google Gemini, Groq, OpenRouter, or any OpenAI-compatible endpoint. Your key, your choice, one settings tab each.

No tokens, no accounts

Speech and speaker models ship inside the installer. No HuggingFace token, no sign-up, no external server to stand up first.

Privacy-first, by design

Research interviews, staff meetings, counselling sessions — the conversations worth analysing are exactly the ones that should not sit on someone else's server.

For researchers

Qualitative interviews and focus groups, transcribed and diarised without the audio ever leaving your machine — then organised into projects you can search, tag, and interrogate across participants.

For educators & teams

Debrief lectures, tutorials, and meetings: see how balanced the discussion was, who spoke and for how long, what themes kept coming up — and get the summary before the next session.