AI Models Catalog
Add the transcription and enhancement models VoiceInk can use.
What the Catalog Is For
The AI Models catalog is where you make models available to VoiceInk.
After a model or provider is available, choose it inside a Mode. This keeps model setup separate from writing behavior: the catalog manages what VoiceInk can use, and Modes decide when to use it.
Model Types
| Type | Use It For |
|---|---|
| Local models | On-device transcription and enhancement options such as VoiceInk Refine, Ollama, and Local CLI. A CLI command may still use a cloud service. |
| Cloud providers | Hosted transcription and enhancement models connected with your own API key. |
| Custom models | OpenAI-compatible transcription or chat-completion endpoints. |
Local Models
Local transcription models run on your Mac after downloading the required files. Availability and performance depend on your hardware and language.
VoiceInk supports Parakeet, Nemotron, Whisper, Cohere Transcribe, SenseVoice, Apple Speech, and imported Whisper .bin files. Text enhancement options include VoiceInk Refine, Ollama, and Local CLI. See Local Models.
Cloud Providers
Cloud providers are useful when you want a hosted transcription model, a hosted enhancement model, or better performance on a Mac that is not a good fit for local processing.
Provider API keys are stored in macOS Keychain, and the provider's models become available inside Modes after connection. See Cloud Providers.
Custom Models
Custom models let you connect your own OpenAI-compatible transcription or enhancement endpoint.
Use this when you have a private server, local gateway, or provider endpoint that is not listed directly in VoiceInk. See Custom Models.
Shared Settings
Use the gear button in AI Models for Model Settings, including filler words, Whisper recognition hints, model prewarming, and timeouts. The Mode editor selects models and configures each workflow.
See VoiceInk Refine, Local CLI, and Real-time Transcription for their requirements and limitations.