February 2025 Summaries

** Octave is a state-of-the-art large language model trained to understand and synthesize speech, offering a new level of expressiveness and nuance in text-to-speech capabilities. In a blind comparison study with 180 human raters, Octave's outputs were favored over ElevenLabs Voice Design in terms of audio quality, naturalness, and how well speech generations matched descriptions of the desired voice. Octave can predict the tune, rhythm, and timbre of speech, inferring when to whisper secrets or shout triumphantly, and transforming that understanding into lifelike speech. The model can also generate voices from prompts, take instructions to modify the emotion and style of a given utterance, and create any AI voice you can imagine. Octave is available today on platform.hume.ai and through its API, offering developer tools such as Voice Design, Acting Instructions, and a voice library of over 40+ premade voices. The model has also been benchmarked against ElevenLabs in an internal evaluation, which showed that Hume's Octave outperformed the industry-leading TTS system across all three human preference metrics: audio quality, naturalness, and description/prompt match. An Expressive TTS Arena is being launched to facilitate broader comparative assessments of expressive speech synthesis, making it an ideal tool for evaluating how well new TTS systems handle nuanced, creative, and emotionally rich content and prompts typical of real use cases.

Octave Text-to-Speech (TTS) is a state-of-the-art voice AI model that enables the interpretation of text meaning and can be customized for any character, guiding emotional delivery and bringing stories to life with human-like expression. The speech-language model (speech LM) is trained on data capturing nuances of human vocal expression and can interpret plot twists, emotional cues, and character traits within a script or prompt, transforming them into lifelike speech. To create the best possible samples and leverage the capabilities of this speech LM, users should craft their prompts with consideration for semantic alignment and character match, experiment with punctuation, incorporate emotions, and develop detailed characters for their voice. The tool also supports multilingual prompting, currently in English and Spanish, with plans to support more languages in the coming weeks.

** The study by Hume and a Fortune 100 automotive company found that drivers prefer voice assistants with personality and emotional intelligence over those focused solely on utility, resulting in a 79% increase in user engagement for the former. The collaboration explored how an AI that responds to users' emotions could create richer, more personalized driving experiences, ultimately concluding that emotional depth and memory are essential for voice AI in vehicles. Drivers valued the ability of the Empathic Voice Interface (EVI) to foster genuine connections, remember past conversations, and provide emotional support, leading to increased loyalty and a sense of companionship on the road.

Pressmaster.AI developed an AI-powered interview system using Hume's Empathic Voice Interface (EVI) to create polished thought leadership content, transforming the traditional time-consuming process of content creation into a 93% faster one. The platform offers four distinct interview modes and uses EVI's emotional intelligence to understand nuances in conversations, making users' ideas feel heard and understood, leading to more authentic and impactful content. With this integration, Pressmaster.AI has seen a 30% increase in demo-to-paid conversion rates and a 40% increase in content creation activity driven by conversational features, revolutionizing how customers create content and build personal brand and company credibility. The platform's natural conversational approach enables users to share their expertise effortlessly, develop half-formed ideas, and preserve their unique voice and perspective, while also recognizing unexpected connections between topics. As Pressmaster.AI expands its platform into a comprehensive marketing assistant, they aim to provide even more personalized and emotionally intelligent content creation experiences through Hume's continued innovation in empathic voice interfaces.