Audar-TTS-V1 is an Arabic-first, open-weight expressive text-to-speech model. Control delivery with inline tags like [laughs] and [whispers], and generate natural speech across MSA, dialects, and Arabic-English code-switching — straight from raw text, no phonemizer or G2P. Ships with a set of natural synthetic voices. The Flash and Turbo tiers are free to download, fine-tune, and self-host. Built for voice agents, media, education, and accessibility.
Most speech recognition models are trained on clean English and fall apart on Arabic — especially dialects and the code-switching people actually use every day. Audar is built Arabic-first: open-weight ASR models covering MSA, dialectal Arabic, and code-switching, trained on real-world audio instead of studio recordings. Inspect the weights, fine-tune on your own data, and deploy without lock-in. Built for developers and researchers building for the 400M+ people who speak Arabic.
