Feature availability
The table is rendered from the public product-fact inventory. It lists implemented behavior, not an unbounded platform or artifact-support claim.
| Capability | Status | Current behavior |
|---|---|---|
| Imported audio and video processing | Available | Select an audio or video file, create a session, convert the selected media, transcribe it, and start summary generation. |
| FFmpeg audio conversion | Available | Convert selected media to 16 kHz mono PCM WAV before transcription. |
| Local Whisper transcription | Available | Transcribe normalized audio by running a local whisper.cpp command-line binary with a locally stored model. |
| Local Ollama summaries and chat | Available | Generate summaries, session chat answers, and global chat answers through a local Ollama HTTP runtime when Local Mode is selected. |
| Live microphone recording | Beta | Create a session while capturing the default microphone and then run the normal conversion, transcription, and summary pipeline. |
| macOS system-audio capture | Beta | System-audio capture is a macOS beta capability and still requires manual validation on each supported release configuration. |
| Session metadata | Available | Store and edit a session title, meeting date, participant names, and description. |
| Early and progressive summarization | Beta | Start summary passes from streamed transcript segments and merge later segment batches before the final session state is persisted. |
| Per-session chat | Available | Ask questions using a session transcript, optional summary, prior chat turns, and the selected local or remote AI provider. |
| Global session indexing | Beta | Split stored transcripts into local SQLite full-text chunks and optionally add local semantic embeddings in the background. |
| Global cross-session chat | Beta | Retrieve relevant content across indexed sessions, show source cards, and generate a streamed answer with the selected local or remote AI provider. |
| Voice input for chat | Beta | Record microphone-only voice input, transcribe it locally with Whisper, and place the resulting text into chat input. |
| Whisper model management | Available | List, download, cancel downloads for, select, and delete the Whisper models in the application catalog. |
| Ollama model management | Beta | List installed Ollama models and download, select, or delete models through the local Ollama runtime. |
| Light and dark appearance | Available | Switch between light and dark application themes and persist the selection in webview local storage. |
| OpenAI-compatible remote provider | Beta | Selecting a remote provider can transmit transcript, summary, prompt, retrieved context, conversation, and embedding input to the configured endpoint. |
Speaker diarization, transcript export, and stable original-audio export are not public current capabilities. Review product limitations before planning a workflow around them.