@hume_ai
Today we're releasing our first open source TTS model, TADA! TADA (Text Audio Dual Alignment) is a speech-language model that generates text and audio in one synchronized stream to reduce token-level hallucinations and improve latency. This means: ā Zero content hallucinations across 1,000+ test samples ā 5x faster than similar-grade LLM-based TTS ā Fits much longer audio: 2,048 tokens cover ~700 seconds with TADA vs. ~70 seconds in conventional systems ā Free transcript alongside audio with no added latency