Modulate Velma
Velma is a voice-native AI model developed by Modulate as part of a broader voice intelligence platform, designed to understand conversations directly from audio rather than relying on text transcripts. Unlike traditional systems that convert speech into text and analyze it with language models, Velma uses an Ensemble Listening Model (ELM), a specialized architecture that processes multiple dimensions of voice simultaneously, including tone, emotion, pacing, intent, and behavioral signals. This allows it to capture the full meaning of a conversation, not just the words spoken, recognizing nuances such as stress, deception, sarcasm, or escalation in real time. It operates by combining hundreds of specialized detectors, each focused on specific aspects of speech like emotional state, inappropriate conduct, or synthetic voice indicators, and then fusing those signals into higher-level insights about what is happening in a conversation.
Learn more
MiniMax Speech 2.8
MiniMax Speech 2.8 is a next-generation AI speech model built to make synthetic voice feel alive, expressive, and deeply human. It focuses on performance in real-world voice agent scenarios, combining ultra-fast response, richer emotional expression, cleaner audio, and stronger cross-lingual performance for products that need natural spoken interaction. Speech 2.8 is designed to reduce the distance between AI voice and real human communication, giving developers and creators more control over how a voice sounds, reacts, and carries meaning. It supports flexible emotion control, allowing users to shape delivery with moods, tone, and expressive direction instead of relying on flat or robotic speech. It can produce speech with more natural pauses, cadence, emphasis, and emotional texture, helping AI characters, assistants, narrators, and interactive agents sound more believable across longer conversations.
Learn more
Griffin
Griffin is Tavus’s first Human Interaction Model, a full-duplex video-to-video system designed to understand and generate face-to-face human interaction in real time. Unlike traditional conversational systems that process speech recognition, language modeling, and speech synthesis sequentially, Griffin continuously perceives audio and video, decides when and how to respond, and generates expressive speech and video at the same time. It pays attention not only to words, but also to tone, gaze, facial expression, gestures, pauses, interruptions, and the surrounding visual context. The model can backchannel, yield or take the conversational turn, react to interruptions, remain engaged during silence, and adjust its emotional tone and nonverbal behavior as the interaction changes. Griffin generates the full visual scene from a reference image, including the face, body, hands, chair movement, shadows, and background, rather than animating only a talking head.
Learn more
HunyuanVideo-Avatar
HunyuanVideo‑Avatar supports animating any input avatar images to high‑dynamic, emotion‑controllable videos using simple audio conditions. It is a multimodal diffusion transformer (MM‑DiT)‑based model capable of generating dynamic, emotion‑controllable, multi‑character dialogue videos. It accepts multi‑style avatar inputs, photorealistic, cartoon, 3D‑rendered, anthropomorphic, at arbitrary scales from portrait to full body. Provides a character image injection module that ensures strong character consistency while enabling dynamic motion; an Audio Emotion Module (AEM) that extracts emotional cues from a reference image to enable fine‑grained emotion control over generated video; and a Face‑Aware Audio Adapter (FAA) that isolates audio influence to specific face regions via latent‑level masking, supporting independent audio‑driven animation in multi‑character scenarios.
Learn more
