Open source

Open Source Notices

Unitra AI is built with the help of these open source projects and their licenses.

Last updated: September 28, 2026

Libraries & Frameworks

Tauri MITApache-2.0

Tailwind CSS MIT

Serde MITApache-2.0

cpal Apache-2.0

Symphonia MPL-2.0

Runtime Components

sherpa-onnx Apache-2.0

ONNX Runtime MIT

DirectML Microsoft Software License Terms

llama.cpp / ggml MIT

LLVM OpenMP runtime Apache-2.0 WITH LLVM-exception

AI Models

IBM Granite Speech 4.0 1B Apache-2.0

Qwen3-ASR 0.6B (Alibaba Cloud) Apache-2.0

Zipformer ASR, English (icefall / LibriSpeech) Apache-2.0

Zipformer ASR, Chinese (icefall multi-zh-hans) Apache-2.0

Zipformer ASR, Japanese (ReazonSpeech, Reazon Human Interaction Lab) Apache-2.0

Zipformer ASR, Russian (Vosk / Alpha Cephei) Apache-2.0

Zipformer ASR, Vietnamese (VietASR) Apache-2.0

NVIDIA NeMo Fast Conformer Hybrid CTC (13 languages) CC-BY-4.0

Whisper tiny, language identification (OpenAI) MIT

TEN-VAD (Agora) Apache-2.0 + conditions

PaddleOCR Apache-2.0

SaT sentence segmenter (wtpsplit) MIT

XLM-RoBERTa tokenizer (Facebook AI) MIT

ECAPA-TDNN speaker encoder (SpeechBrain) Apache-2.0

This page lists the open source components distributed with the Unitra AI desktop application. The license texts and attribution notices required for the AI models and runtime components above ship with the application and can be read in its settings. NVIDIA NeMo models are used under CC-BY-4.0, converted to ONNX and quantized without retraining; no endorsement by NVIDIA is implied. Trademarks are the property of their respective owners. For compliance inquiries: legal@unitra.ai.