Hume AI
@hume_ai
The foundational speech-language model with emotional intelligence. Available via TTS or Speech-to-Speech
2024: Voice Cloning 2025: What about personality cloning? Hume’s voice AI can now not only mimic your voice but also speaking style and language. It’s now available via our TTS and new speech-to-speech model, EVI 3, which is also launching today.
It's free to get started with Hume's EVI 3 and @GroqInc's Kimi K2!
You can now use Groq’s Kimi K2 to build super realistic speech-to-speech voice interfaces with emotion via @hume_ai 's new EVI 3. Perfect for AI companions, phone calls, or anything you’re working on. Link in comments.
We're excited to partner with @Vapi_AI to offer Hume's real-time expressive TTS on their platform at 150ms latency and 2c/minute!
We've rolled out significant improvements to the @hume_ai AI TTS integration in Vapi. The latest update delivers: • 66% lower latency • Reduced cost per min by 41% • More efficient voice interactions This aligns with our ongoing effort to enhance speed, reliability, and…
Need voices that sizzle with emotion? ❤️🔥 Hume’s serving up alien barbecue goodness at platform.hume.ai
.@hume_ai's @gagnecr13 & @inafried test out Hume AI's EVI 3 AI model that's optimized to understand and express human emotions at #AxiosAISummit
Today at 5:15 pm ET, we'll be at the @axios AI+ NY Summit! Our VP of Research Chris Gagne (@gagnecr13) will be joining @InaFried on stage to demo EVI 3. Watch the livestream to learn more about empathic AI: axios.com/2025/05/29/axi…
Just launched TTS Arena V2! 🎙️ Blind A/B voting for TTS models (open + closed) 🗣️ New: Conversational Arena (CSM 1B, Dia 1.6B, more) 📊 Personal Leaderboard to track your favorites (optional login) ⚡ Rebuilt from scratch - faster + keyboard shortcuts