Articles about AI Audio in Technology & AI
We've all heard AI voices that just sound wrong. Mistral's new Voxtral TTS aims to fix that with a clever hybrid approach that gives AI speech the human touch it's been missing.
Google just dropped Lyria 3, an AI that creates custom music tracks—complete with vocals—from a simple text prompt or even a photo. We break down how it works, why it's different, and what it means for the future of creativity.
This week in tech was a total rollercoaster. We saw a cybersecurity expert targeted by death threats, while AI gave a musician with ALS his voice back. Let's unpack the good, the bad, and the downright weird of what's happening.
Microsoft just released VibeVoice-ASR, a new open-source AI that can transcribe an entire hour of audio in a single pass. It even knows who said what, when, and understands your custom jargon.
Ever wished you could magically remove a barking dog from a recording or lift a guitar solo from a noisy concert? Meta's new AI, SAM Audio, does just that, using simple text, visual, or time-based prompts to separate any sound from a mix.
Ever notice that awkward pause while your AI assistant thinks? Microsoft's new VibeVoice-Realtime AI model aims to fix that, generating speech in just 300 milliseconds. Let's break down how it works and why it matters for the future of voice AI.
Ever feel like audio AI models are just reading a script instead of truly listening? A new model, Step-Audio-R1, is changing that by forcing AI to ground its reasoning in actual acoustic cues, finally making "thinking longer" a benefit, not a bug.