Text-to-Speech
A new research paper explores how neural networks can automate the evaluation of text-to-speech systems, replacing costly human assessments with learned quality metrics for synthetic speech.
Voice AI
A deep dive into the modern voice AI pipeline — from Whisper's speech recognition to neural TTS and voice synthesis — mapping every layer of the stack powering today's conversational AI and raising new questions about audio authenticity.
Voice AI
A technical breakdown of modern voice AI architecture reveals a three-layer 'sandwich' of ASR, LLM reasoning, and TTS synthesis — the same pipeline powering voice cloning and real-time conversational AI.
Voice Synthesis
Mistral AI releases Voxtral TTS, a 4-billion parameter open-weight streaming text-to-speech model supporting low-latency multilingual voice generation with implications for synthetic media.