Custom Models

Neuron Flame supports two local model families and any OpenAI-compatible cloud transcription endpoint. Pick what fits your hardware, language, and accuracy needs.

Parakeet V2 (default)

Whisper family

OpenAI's Whisper, ported to whisper.cpp by Georgi Gerganov. Multiple sizes:

ModelSizeSpeedAccuracyLanguages
Tiny78 MBFastestLowest100+
Base148 MBVery fastGood100+
Small244 MBFastBetter100+
Medium770 MBModerateGreat100+
Large v31.6 GBSlowerBest100+
Large v3 Turbo815 MBFastExcellent100+

The Turbo variant is a special case: it's a distilled Large with comparable accuracy at half the size and twice the speed. Often the right choice if Parakeet's English-only is a dealbreaker.

Downloading a Whisper model

  1. Open the AI Models tab.
  2. Find the model in the list.
  3. Click Download. Progress shows in the row.
  4. Once complete, click Use this model.

Models live in ~/Library/Application Support/com.neuronflame.app/Models/. You can delete unused ones to reclaim space.

Custom OpenAI-compatible endpoints

Want to use a hosted Whisper API (e.g. Groq's blazing-fast Whisper Large), a self-hosted Whisper server, or any other endpoint that speaks OpenAI's /v1/audio/transcriptions protocol? Add it as a Custom Cloud Model.

  1. AI Models tab → + Add Custom Provider.
  2. Enter a name (e.g. "Groq Whisper").
  3. Base URL — e.g. https://api.groq.com/openai/v1.
  4. API key.
  5. Model name — e.g. whisper-large-v3-turbo.
  6. Save and select.

When to use cloud transcription: mainly when you want Whisper Large quality without the local compute cost. Groq is currently the speed champion. For privacy-sensitive work, stick with local — Parakeet on Apple Silicon is competitive with Whisper Large in real-world use.

Picking the right model — quick guide

Custom dictionary

Independent of the model, the Custom Dictionary lets you correct transcribed text by matching patterns and replacing with your preferred spelling. It runs after transcription but before AI enhancement, so:

Common entries: