Best Local AI for Meeting Notes and Transcription
Which speech-to-text model and which local LLM fit together on your GPU, from no GPU to 24 GB, and how long a meeting the summariser can read in one pass.
Tag
Which speech-to-text model and which local LLM fit together on your GPU, from no GPU to 24 GB, and how long a meeting the summariser can read in one pass.
Which tool-calling local models to point Home Assistant's Ollama integration at, by GPU tier, plus the local speech pieces and the limits HA documents.