AI Enhancement

The raw transcript is just the beginning. AI Enhancement passes it through a language model with a prompt of your choice — to fix grammar, reformat for email, condense rambling, prettify code, translate, summarise, or anything else you can describe in a system prompt.

It's optional. Neuron Flame works perfectly fine without it. Enhancement is a layer on top — turn it on only when you want polish.

Supported providers

ProviderModelsWhere it runs
Google GeminiFlash, Pro, Flash LiteGoogle cloud
OpenAIGPT-4o, GPT-4o-mini, etc.OpenAI cloud
AnthropicClaude 3.5 Sonnet, HaikuAnthropic cloud
OllamaLlama, Mistral, Qwen, anything localYour Mac
GroqLlama 3.3, MixtralGroq cloud (fast)
Custom OpenAI-compatibleAny URL + model nameWherever you point it
Local CLIAny executableYour Mac

Setting up

  1. Open the AI Models tab.
  2. Choose a provider.
  3. Paste your API key (Gemini and Anthropic offer generous free tiers).
  4. Pick a model from the dropdown.
  5. Toggle Enable AI Enhancement on.

That's it. Every transcription now flows through the model before being pasted.

Prompts

Neuron Flame ships with a curated set of prompts:

You can edit these or create your own. Each prompt has a system message and an optional user-message template — both support variables like {{transcript}}, {{clipboard}}, and {{window_context}}.

Context-aware enhancement

Two optional toggles make the model smarter:

Both are off by default. Both are processed locally and sent only to the model you've configured. Neither is ever written to disk.

What happens if it fails?

If the LLM call fails — rate limit, network blip, invalid key, anything — Neuron Flame falls back to the raw transcript. You always get something pasted; you never get an error string in your document. The History tab shows the raw transcript only (the failed enhancement is not stored).

Custom prompts

The prompt editor uses Markdown for the system message. Variables you can reference:

The wrapper artifacts (<TRANSCRIPT> tags etc.) are stripped from the model's reply automatically — even if it tries to echo them back, they won't end up in your text.

Privacy notes

See the full Privacy doc for the complete data-flow diagram.