All activity
Introducing Octave 2.
What’s new:
- Fluent in 11+ languages
- 40% faster (<200ms latency) & 50% cheaper than Octave 1
- Multi-speaker conversation
- More reliable pronunciation
- New voice conversion & phoneme editing capabilities
Octave 2 by Hume AIThe next-generation multilingual text-to-speech model
Zach Krallleft a comment
Congrats on the launch! Love the focus on ADHD-friendly design—this looks like it’ll really make a difference.
Saner.AI 1.0First ADHD-friendly AI assistant for notes, email, calendar
Zach Krallleft a comment
Hi everyone! Really excited that we can share what we have been building recently. EVI 3 is another step toward general voice intelligence. It is a speech-language model that can understand and generate any human voice, not just a handful of speakers. With this broader voice intelligence comes greater expressiveness and a deeper understanding of tune, rhythm, timbre, and speaking style. Leave a...
EVI 3: Understand and generate any voiceHume AI's new voice that truly understands emotion
Hume AI's EVI 3 is a new speech-language model for highly expressive, realistic & emotionally intelligent voice AI. Generates any voice/personality from prompts. Outperforms GPT-4o in empathy & naturalness.
EVI 3: Understand and generate any voiceHume AI's new voice that truly understands emotion
The first LLM for text-to-speech. While other TTS just “reads” words, Octave grasps their meaning. Create any AI voice with a descriptive prompt, guide its emotional delivery (angrier! more sarcasm!), and bring your stories to life with human-like expression.
Octave TTSDescribe any AI voice and prompt its emotional delivery