Speaking of Voxtral

Navigating the challenges and opportunities of synthetic voices

We’re sharing lessons from a small scale preview of Voice Engine, a model for creating custom voices.

TTS Arena: Benchmarking Text-to-Speech Models in the Wild

Voxtral transcribes at the speed of sound.

Introducing GPT-Live

A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.

VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion

arXiv:2607. 11706v1 Announce Type: cross Abstract: Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech that differs from the generators represented in many legacy spoofing benchmarks.

Expanding on how Voice Engine works and our safety research

Exploring the technology behind our text-to-speech model.

Voxtral

VoiceDesigner: Text-to-Voice Generation and Editing via Unified Diffusion Modeling and Data Augmentation

arXiv:2608. 13613v1 Announce Type: cross Abstract: Recent breakthroughs in generative models have made text-to-voice generation (TTV) possible, enabling the synthesis of speech directly from textual voice descriptions.

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

arXiv:2606. 10029v1 Announce Type: cross Abstract: Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream.

dots.tts Technical Report

arXiv:2606. 07080v1 Announce Type: cross Abstract: We present dots.

Liberating LLM Capabilities in Full-Duplex Speech Models

arXiv:2606. 07547v1 Announce Type: cross Abstract: Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and suppresses text-native capabilities such as code generation, structured analysis, and multi-step reasoning in realtime interaction, for tasks that require persistent, structured, and inspectable intermediate outputs.

How we built a realtime system for responsive voice AI in six months

GPT-Live enables continuous voice interaction with AI, using a turnless speech model and low-latency architecture for faster, more natural conversations.