arXiv:2607. 14846v1 Announce Type: cross Abstract: Current voice AI benchmarks typically evaluate isolated capabilities such as speech intelligibility, word error rate, or text-based dialogue quality, but they rarely test whether systems harness the acoustic information that distinguishes spoken language from its textual representation.
A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.
Explore new realtime voice models in the OpenAI API that can reason, translate, and transcribe speech, enabling more natural and intelligent voice experiences.
Our latest voice model has improved precision and lower latency to make voice interactions more fluid, natural and precise.
We’re sharing lessons from a small scale preview of Voice Engine, a model for creating custom voices.
GPT-Live enables continuous voice interaction with AI, using a turnless speech model and low-latency architecture for faster, more natural conversations.
arXiv:2608. 15411v1 Announce Type: new Abstract: The ability of artificial intelligence (AI) models to generate highly realistic human voices has advanced rapidly.
Developers can now build fast speech-to-speech experiences into their applications
How OpenAI rebuilt its WebRTC stack to power real-time Voice AI with low latency, global scale, and seamless conversational turn-taking.
arXiv:2606. 18611v1 Announce Type: cross Abstract: We propose a parameter-efficient speech enhancement framework, Quaternion Conformer GAN (QC-GAN), which combines a Quaternion Conformer generator with MetricGAN-based training.
arXiv:2608. 10716v1 Announce Type: cross Abstract: Speech-to-speech (S2S) voice agents are increasingly being incorporated into enterprise for customer care and as daily companions for consumers owing to the ease of the conversational modality over text.
