RT @krandiash: We released Sonic-3.5 and Ink-2, the #1 streaming models for text to speech and speech to text you can use in your voice age…
Together has released two new models: Sonic-3.5 for text-to-speech and Ink-2 for speech-to-text. These models are designed for real-time streaming applications and are claimed to be the top-performing models in their respective categories. Together is now the sole provider offering leading models for both audio input and output. AI
IMPACT Provides new open-source options for real-time speech processing, potentially lowering costs and increasing accessibility for developers.