Skip to content
← Help

Configuring AI providers and defaults

Your finished transcript and speaker labels always run on your computer with the bundled local models — there's nothing to configure for those. The Providers section covers the optional AI piece: the provider that writes your summaries and powers Q&A, chapters, the Analyzer, and transcript polish. Every cloud provider is optional and uses your own API key, billed directly to you. Daisy never proxies or marks up that usage.

You can pick a cloud provider (Groq, OpenAI, or Anthropic), a keyless local server (LM Studio or Ollama), or None to skip AI and use the copy-paste workflow. Transcription never needs a provider — it always runs on-device.

Add an AI provider

  1. Go to Settings and open the Providers section.
  2. Under AI provider, pick the provider you want to use (Groq, OpenAI, Anthropic, LM Studio, or Ollama). The section shows a single editor for the provider you select.
  3. Select Configure (or Edit if a key already exists).
  4. Step 1 of 2 — paste your API key, and adjust the Base URL only if you need to. LM Studio and Ollama are keyless, so there's no key field — Daisy just needs the base URL of the running server.
  5. Select Test key & list models (or Test connection & list models for keyless local servers). Daisy makes one call to confirm the connection works and pulls the list of available models.
  6. Step 2 of 2 — pick a model from the list, or type a custom model name in the field below it, then select Save.

Picking a provider in this dropdown also makes it your default for AI features — there's no separate step. To remove a stored key later, reopen the editor and select Clear key.

Live captions need no provider

Live captions run on-device with the bundled model. A quick speed check decides per machine whether they appear while you record — see Live and real-time transcription.

Advanced: local transcription model

Under Advanced → Local transcription model, you can swap the on-device Whisper model Daisy uses for the finished transcript. The app ships with a bundled model, so this is optional.

Set your defaults

In Settings, open the Recordings section to choose what Daisy uses by default:

  • Default microphone — the input device for new recordings.
  • Speech level (advanced) — fine-tune the input level Daisy treats as speech.
  • AI provider — the same provider dropdown as above (summary, Q&A, chapters, analysis, polish). "None" uses copy-paste.
  • Text size — the whole-UI zoom.
  • Live captions — Auto (follow the per-machine speed check), On, or Off. See Live and real-time transcription.
  • Echo cancellation (AEC) — Auto, Always, or Never, for removing speaker echo from your microphone track.
  • Noise suppression — clean up background noise in saved audio. Off by default; tick it to turn it on.
  • Updates — check for new versions automatically.
  • Diagnostics — debug logging level, plus a button to open the logs folder.