GPT-Live-1 mini
GPT-Live-1 mini is one of the two GPT-Live voice models rolling out to ChatGPT users globally, designed to bring more natural, intelligent, and responsive voice interaction to everyday conversations. Built with the same full-duplex approach as GPT-Live, it can listen and speak at the same time instead of waiting for rigid turn-by-turn exchanges. The model continuously processes input while generating output, allowing it to decide many times per second whether to speak, keep listening, pause, interrupt, or invoke a tool. This makes conversations feel faster, smoother, and more natural, with active listening, quick back-and-forth, better timing, and fewer awkward interruptions when the user pauses to think. GPT-Live-1 mini also benefits from the new ChatGPT Voice experience, where users can interrupt with a question, ask ChatGPT to slow down, or tell it to stay quiet and listen.
Learn more
StepAudio 3
StepAudio 3 is StepFun’s next-generation audio model family, built to understand, generate, and interact through voice, sound, and music. The lineup includes StepAudio 3 Realtime for natural full-duplex conversation, StepAudio 3 ASR for speech recognition, StepAudio 3 TTS for speech synthesis, StepAudio 3 Gen for general-purpose audio generation, and StepAudio 3 Music for long-form music creation. Realtime is designed around a continuous listen-converse-think-act loop, understanding not only words but also hesitation, laughter, emotion, pauses, backchannels, and interruptions. It can think while speaking, reason through harder questions without breaking conversational flow, and use tools to complete tasks once it understands the user’s intent. StepAudio 3 Gen unifies zero-shot TTS, voice design, vocal generation, sound effects, music, and mixed audio generation within one framework, while StepAudio 3 Music supports text-controlled songs, instrumentals, vocal arrangement, and more.
Learn more
Dessa
Dessa is Block's speech-to-speech artificial intelligence model for conversational voice research and applications. It takes audio input and produces audio output directly, without converting speech into text as an intermediate step. Trained from scratch on human conversation rather than text, the model supports full-duplex interaction, listening and speaking at the same time, and runs locally on a MacBook Pro with an M4 Max chip or better. It captures conversational cues such as emotion, sarcasm, laughter, pauses, and turn-taking that can be lost in text-based pipelines. Dessa is intended for AI safety researchers and developers studying voice-model behavior, privacy, and real-time interaction. It is a speech model for research and development, not a general-purpose business application or hosted voice-agent platform.
Learn more
GPT-Live-1.1 Quip
GPT-Live-1.1 Quip is an advanced voice AI model designed to make conversations with artificial intelligence feel more natural and intelligent. As the successor to GPT-Live-1, it delivers full-duplex voice interaction, allowing users to speak and receive responses continuously instead of waiting for clearly defined conversational turns. The model can follow pauses, interruptions, and changes in speaking pace, deciding in real time whether to respond or continue listening. This creates a more fluid, responsive experience that closely resembles natural human conversation. GPT-Live-1.1 Quip supports voice interactions across ChatGPT, Codex, and Dots, providing conversational capabilities for different AI-assisted workflows. The model incorporates safety training, voice-specific evaluations, and system-level safeguards designed to promote responsible interactions. Its training uses diverse datasets with filtering processes to maintain data quality.
Learn more
