SpeaklySpeakly

LLM Providers

Configure AI providers for post-processing

Post-processing runs your matching Custom Prompts rule over the transcribed text with an LLM. It is configured in Settings → Post-Processing.

Two modes

  • Ollama (Local) — badged 100% Offline: "Private local LLM processing on your device".
  • Your API Key — badged BYOK: you supply a key for one of the cloud providers below.

BYOK providers

Pick one under Provider:

  • Groq — Ultra-fast inference
  • OpenAI — GPT models
  • Anthropic — Claude models
  • Google Gemini — Fast & cheap
  • Mistral — European, GDPR
  • OpenRouter — 100+ models
  • Cerebras — Ultra-fast

Model lists are fetched, never hardcoded

Speakly ships no list of model names. Paste a valid key and it asks the provider which models your account can use, then fills the dropdown from that answer. If a model you had saved disappears upstream, Speakly switches to one that still exists rather than failing with a 404.

Until a valid key is present the field shows a message instead of a dropdown:

  • Add a valid API key to load available models. — no key yet
  • Loading models… — the fetch is in flight
  • No models found — check that your API key is valid. — the provider rejected the key

Defaults on a fresh install

  • Ollama Endpoint: http://127.0.0.1:11434
  • Model Name (Ollama): llama3
  • OpenAI model: gpt-5.6-luna
  • Groq model: openai/gpt-oss-120b
  • Google Gemini model: gemini-3.6-flash

Anthropic, Mistral, OpenRouter and Cerebras have no shipped default — their model is chosen from the fetched list once your key is in.

Google Gemini takes a Google AI Studio key (aistudio.google.com/api-keys) — the same key the Google transcription engine uses; saving it in either place fills in the other. The dropdown lists Gemini text models only (no TTS, transcription, image or robotics models). Gemini 3 models think before they answer; Speakly asks for low reasoning effort so a rewrite stays quick, and a saved model that Google has since closed to your account falls back to gemini-3.6-flash.

Using Ollama

  1. Install Ollama from ollama.com.
  2. Run ollama serve, then ollama pull llama3.
  3. In Settings → Post-Processing, pick Ollama (Local).
  4. Leave Ollama Endpoint at http://127.0.0.1:11434 and set Model Name to the model you pulled.
  5. Click Test Connection. It reports Connected or Connection failed.
Use 127.0.0.1, not localhost
The app's own setup note says to use 127.0.0.1 instead of localhost to avoid connection issues, and it rewrites a stored localhost endpoint to 127.0.0.1 on load.
LLM Providers — Speakly