Nextcloud App Store
Chris 0:00
Morning everyone. Let's keep it quick today.
Record and transcribe on Nextcloud
Your team already owns the infrastructure. Cassini adds meeting transcription to the stack, processed entirely on your sovereign server.
cassini
~ cassini record --room daily-standup
Nextcloud Talk · daily-standup · 5 participants
●Recording 00:02:45
✓Transcribingparakeet-tdt-0.6b-v3 · local
✓Packaging
→ daily-standup-2026-07-01.opus
The basics, covered
Speaker ID
Every line attributed to the right voice, automatically.
Group & 1:1 calls
Works with any Nextcloud Talk room.
Built inside Nextcloud
Read transcripts and replay audio without leaving Nextcloud.
Daily standup
Tue, 1 Jul 2026 · 3 min · Chris, Silvio, Marco, Ivan, Alex
Silvio 0:18
Auth refactor is done, pushed to staging. Picking up the notification service today.
Marco 0:45
Found the race condition — fix going up today.
0:18 2:45
Data privacy
100% local processing
Your data, your rules
CPU
sherpa-onnxRuns on your server. No GPU required. Works on any standard Nextcloud setup — audio never leaves your infrastructure.
GPU
NVIDIA ParakeetCUDA-accelerated. Drop in the CUDA image and Cassini auto-detects your GPU. Same privacy guarantees — significantly quicker for heavier workloads.
One file.
Everything inside.
Audio, transcript, and metadata in one self-contained .opus file.
Audio
Opus-encoded, 48kbps
Transcript
Speaker-labelled, plain text
Metadata
Room, participants, timestamps
Optional
Meeting summaries
Point Cassini at an LLM — an OpenRouter API key, or any OpenAI-compatible endpoint you host yourself — and it will generate a structured summary, automatically, after every meeting. Leave it unconfigured and the local transcript is published as-is.
The team ran a quick check-in. Silvio completed the auth refactor and pushed to staging, and is picking up the notification service next. Marco identified and is fixing a race condition in today's build.
Key points
- Auth refactor complete — on staging
- Race condition identified, fix shipping today
- Notification service is next priority
Ready to get started? Read the docs →
Questions?
We've got answers
Need support? Send us an email.
Does audio leave my server?
By default, no. Cassini runs NVIDIA's Parakeet speech-to-text model locally on your Nextcloud server and audio never leaves your infrastructure. The one exception is meeting summaries: if you enable them, the transcript (not the audio) is sent to whichever LLM endpoint you configured — your own or a third party. Summaries are opt-in and off by default.
Which Nextcloud versions are supported?
Cassini supports Nextcloud 27 and above with Nextcloud Talk enabled. Check the marketplace listing for the exact compatibility matrix.
What languages can it transcribe?
The bundled Parakeet model supports 25 European languages, including English, German, French, Spanish, Italian and Dutch. It detects the language automatically, so Cassini transcribes whatever is spoken in the meeting with no configuration needed.
Does it record every call automatically?
Recording is on-demand. A host starts the recording from within the Talk room, giving participants visibility and keeping you in control of which meetings are captured.
Where are recordings stored?
Each recording is saved as a single .opus file in Nextcloud Files, using the same storage and access controls as the rest of your data.