Hume AI Launches Octave 2: Next-Generation Multilingual Text-to-Speech Model
By
Aleksandar Blazhev
Pulled from the oven just right. Trustworthy, fact-dense, deeply satisfying.
Summary
Hume AI has launched Octave 2, their next-generation multilingual text-to-speech model that represents significant improvements over the previous version. Key enhancements include fluency in 11+ languages, 40% faster performance with under 200ms latency, 50% cost reduction, multi-speaker conversation capabilities, improved pronunciation reliability, and new voice conversion and phoneme editing features. The launch is positioned as part of Hume AI's mission to ensure artificial intelligence serves human goals and emotional well-being.
Key quotes
· 4 pulledHume AI just released a new AI voice model called Octave 2
It's an ultra-realistic and expressive text-to-speech model
Fluent in 11+ languages with 40% faster performance and 50% cheaper than Octave 1
Our mission is to ensure that artificial intelligence is built to serve human goals and emotional well-being
You might also wanna read
Hume AI Open-Sources TADA: Text-Acoustic Synchronization for Faster, More Reliable Speech Generation
Hume AI has open-sourced TADA (Text-Acoustic Dual Alignment), a novel speech-language model that addresses fundamental limitations in curren

Microsoft Launches First In-House AI Models MAI-Voice-1 and MAI-1-preview
Microsoft has launched its first in-house AI models called MAI-Voice-1 and MAI-1-preview. The MAI-Voice-1 speech model can generate a minute
Anthropic Releases Claude Haiku 4.5 AI Model with Improved Speed and Lower Costs
Anthropic has released Claude Haiku 4.5, their latest small AI model that offers similar coding performance to the previously state-of-the-a
Microsoft Open-Sources VibeVoice: A Speech-to-Text AI for Long-Form Audio Transcription
Microsoft has open-sourced VibeVoice, a frontier voice AI system that includes VibeVoice-ASR, a unified speech-to-text model capable of hand
