From ffba480d289352daddfcb4b3f81ec03b2f7c804f Mon Sep 17 00:00:00 2001 From: TomiEckert Date: Sun, 1 Mar 2026 22:05:37 +0100 Subject: [PATCH] feat: Expand LLM and Whisper STT provider support to include Fireworks AI and Cerebras, and update related documentation. --- README.md | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 8d59669..d72b94f 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # Toak: High-speed Linux Dictation -Toak is a high-speed, professional-grade dictation tool for Linux. It combines state-of-the-art Speech-to-Text (Whisper via Groq) with LLM refinement (Llama/GPT via Groq or Together AI) to provide a seamless, articulate, and highly configurable dictation experience. +Toak is a high-speed, professional-grade dictation tool for Linux. It combines state-of-the-art Speech-to-Text (Whisper via Groq or Fireworks AI) with LLM refinement (Llama/DeepSeek/GPT via Groq, Together AI, Cerebras, or Fireworks AI) to provide a seamless, articulate, and highly configurable dictation experience. Built with **.NET 10** and compiled to **Native AOT**, Toak runs as a lightning-fast standalone binary with zero runtime overhead, using a client-daemon architecture for near-zero latency. @@ -11,7 +11,8 @@ Built with **.NET 10** and compiled to **Native AOT**, Toak runs as a lightning- - **Blazing Fast**: Uses Groq's API for sub-second Whisper transcription and LLM refinement. - **Native AOT**: Compiled to a native Linux binary for instant startup and minimal footprint. - **Intelligent Refinement**: Automatically fixes grammar, punctuation, and technical terms while preserving your voice. -- **Multi-Provider LLM**: Supports both **Groq** and **Together AI** for text refinement, including Llama 3 models. +- **Multi-Provider LLM**: Supports **Groq**, **Together AI**, **Cerebras**, and **Fireworks AI** for text refinement, including Llama 3 and DeepSeek models. +- **Multi-Provider Whisper**: Easily swap between Groq and Fireworks AI for state-of-the-art STT APIs. - **Reasoning Capabilities**: Optional reasoning effort settings for complex text processing. - **Modular Skills**: Actionable "System" commands for translation, terminal execution, professional rewriting, and summarization. - **Multiple Backends**: Types directly into your active window (`wtype`, `xdotool`, or `ydotool`), copies to clipboard, or pipes to stdout. @@ -26,7 +27,7 @@ Built with **.NET 10** and compiled to **Native AOT**, Toak runs as a lightning- - **Audio Capture**: `pipewire` / `pw-record` (recommended) or `ffmpeg` - **Typing Backend**: `wtype` (Wayland), `xdotool` (X11), or `ydotool` (Virtual Input) - **Clipboard**: `wl-copy` (Wayland) or `xclip` (X11) -- **API Keys**: Groq (required for Whisper) and optionally Together AI. +- **API Keys**: API Keys for your chosen providers (Groq, Together AI, Cerebras, or Fireworks). --- @@ -102,9 +103,10 @@ Run `toak skill add` to build interactive custom capabilities. All skills live i Key settings in `ToakConfig.cs` (managed via `toak onboard` or `toak config`): -- `LlmProvider`: Choice of `groq` (default) or `together`. -- `LlmModel`: The refinement model (e.g., `llama-3.3-70b-versatile`). +- `LlmProvider`: Choice of `groq` (default), `together`, `cerebras`, or `fireworks`. +- `LlmModel`: The refinement model (e.g., `llama-3.3-70b-versatile` or `accounts/fireworks/models/deepseek-v3p1`). - `ReasoningEffort`: Set to `none` (default) or `low` for O1-style reasoning. +- `WhisperProvider`: Choice of `groq` (default) or `fireworks`. - `WhisperModel`: The STT model (default: `whisper-large-v3-turbo`). - `WhisperLanguage`: Set spoken language (e.g., `en`, `es`, `fr`). - `TypingBackend`: Choose between `wtype`, `xdotool`, or `ydotool`.