Dictation models
Switch engines under Settings → Dictation models. First launch defaults to Apple on-device speech in most cases.
What Free allows
Section titled “What Free allows”LicenseManager.isASRProviderAllowed:
| Free | Trial / Pro |
|---|---|
| Apple (on-device) | Full catalog |
| Doubao (BYOK cloud) | Bailian, MiMo, Whisper, Groq, Soniox, NVIDIA, OpenAI-compatible / self-hosted gateways, … |
Pointing Base URL at localhost does not unlock multi-ASR on Free — OpenAI-compatible / faster-whisper still need Trial or Pro.
Common engines
Section titled “Common engines”| Kind | Examples | Network | Plan |
|---|---|---|---|
| On-device | Apple Speech / SpeechAnalyzer | Local (system may download language packs) | Free ✓; no cloud key |
| Regional cloud | Doubao, Bailian, MiMo | Yes | Free: Doubao only; Bailian / MiMo → Trial/Pro |
| General cloud | Whisper, Groq, ElevenLabs, Soniox | Yes | BYOK; Trial/Pro |
| Compatible / self-host | OpenAI-compatible, faster-whisper | Depends | localhost OK; still Trial/Pro |
| NVIDIA | Speech NIM (Parakeet, …) | Yes / self-host | Trial/Pro |
Full list is whatever the in-app catalog shows.
API keys
Section titled “API keys”Stored in the macOS Keychain. Audio goes only to providers you configure. See BYOK.
File transcription
Section titled “File transcription”File import can use a separate model from live dictation. The same Free/Pro provider gate applies. See File transcription.
Local Only Mode
Section titled “Local Only Mode”Public-cloud endpoints fail when Local Only is on. Apple is always allowed; other engines need loopback Base URL / WS and the plan gate above.
Proper nouns
Section titled “Proper nouns”Use each engine’s context / prompt / dictionary fields, then word replacements as a fallback.