Exploring the technology behind our text-to-speech model.
For the first time, developers can also instruct the text-to-speech model to speak in a specific way—for example, “talk like a sympathetic customer service agent”—unlocking a new level of customization for voice agents.
arXiv:2607. 21180v1 Announce Type: new Abstract: Recent advances have introduced speech-to-speech (S2S) conversational assistants capable of producing natural-sounding interactions, including non-verbal cues like tonality and mood.
We’re sharing lessons from a small scale preview of Voice Engine, a model for creating custom voices.
We describe our latest thinking in the hope of helping other AI developers address safety and misuse of deployed models.
arXiv:2606. 03812v1 Announce Type: new Abstract: Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identification.
arXiv:2608. 07535v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning.
arXiv:2606. 05177v1 Announce Type: cross Abstract: Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and text.
Developers can now build fast speech-to-speech experiences into their applications
Explore new realtime voice models in the OpenAI API that can reason, translate, and transcribe speech, enabling more natural and intelligent voice experiences.
A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.
arXiv:2606. 24523v1 Announce Type: cross Abstract: Scam phone calls exploit vulnerable communities worldwide, yet research on detection has focused almost exclusively on English and other high-resource languages.
arXiv:2608. 11590v1 Announce Type: cross Abstract: Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing.