Speech Recognition with Whisper on vLLM: Mel Spectrograms, Streaming, and Who Spoke When
How Whisper turns audio into text, from mel spectrograms to an encoder-decoder; serving it with vLLM, transcribing in real time, and labeling speakers.
Speech AI
Speech recognition and synthesis, served: how the models work, what serves them, and who leads.
Text-to-Speech in 2026: How the Models Work and Who Leads
How modern text-to-speech models turn text into audio tokens and waveforms, the open models that lead today, and how to choose one for latency, quality, and voices.
NVIDIA's Speech Stack: Parakeet, Canary, Nemotron Speech, and Magpie
What NVIDIA's open speech models are for: Parakeet and Canary for recognition, Nemotron Speech for streaming, Magpie for synthesis, and how they fit a voice agent.