Crazy realistic now. We're cooked.
Summary
Dessa is a full-duplex speech-to-speech model that can run on consumer GPUs, being described as a GPT-3 moment for speech.
Similar Articles
GPT New Voice Model is actually insane.
OpenAI's new GPT voice model enables highly realistic, real-time voice conversations with low latency and emotional expression, marking a significant leap in AI voice interaction.
Block’s new voice model sounds eerily human
Block released Dessa, a full-duplex speech-to-speech voice model trained entirely on human speech that runs locally on consumer GPUs and produces expressive, human-like conversation with built-in emotion.
@LinusEkenstam: This is life-changing tech. We need less hype, and more stuff like this. Imagine how many people this can help
Bland launches Speech v3, claiming it's the world's first Human Speech Engine and top model in Design Arena's Audio Realism benchmark, surpassing ElevenLabs, Grok, Cartesia, and OpenAI.
🟩 NVIDIA's whole speech stack just went local. ASR + TTS + codec, quantized to GGUF, running on-device via NeMo-Speech.cpp
NVIDIA's entire speech stack—ASR, TTS, and codec—is now quantized to GGUF and runs locally on-device via NeMo-Speech.cpp, with new model releases for Magpie-TTS, Nemotron Speech Streaming, and Parakeet.
@kwindla: OpenAI shipped a new speech-to-speech model today: gpt-realtime-2 This is the first speech-to-speech model good enough …
OpenAI has released gpt-realtime-2, a new speech-to-speech model optimized for real-time voice agent interactions with low-latency tool calling.