TTS AI news

Focuses on Training-Free Instruction TTS Gender Bias Calibration Using Model-Adaptive Steering.

Focuses on Beyond Token Revision: Investigating Mask-and-Replace Diffusion for Zero-Shot Text-to-Speech.

Focuses on BanglaBox: A Phonetically-Balanced Corpus and Data-Efficient Foundation-Model Adaptation for Bangla Text-to-Speech with Zero-Shot Voice Cloning.

Focuses on Shared-State Local Translations for Training-Free Voice Conversion.

Focuses on Index-Translate: A Multilingual Translation Model Family -- Text, Speech, Controlled Dubbing, and Long-Document Translation.

Hugging Face published Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning.

Focuses on MeanVoiceFlow2: Joint Optimization of Mean Flow and Content Encoder for Fast One-Step Zero-Shot Voice Conversion.

Google DeepMind published Gemini 3.8 text-to-speech says hello.

Focuses on EditVoice: Variable-Length Non-Autoregressive Zero-Shot TTS and Speech Editing with Edit Flows.

Focuses on Not Quite My Tempo: Voice Activity-aware Speech Synthesis for Lip-Synchronous Dubbing.

Focuses on CycleSpeech: Reciprocal Alignment for Instruction-Controlled Speech Synthesis and Paralinguistic Understanding.

Focuses on Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion.

Focuses on GrainSpeech: Less Context, More Detail for Compact Speech Synthesis.

Focuses on Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis.

Focuses on Self-Distilled Pronunciation and Accent Control for Neural Text-to-Speech.

Focuses on Taming Long-form Text-to-Speech.

Focuses on AlignDPO: Preference-Gated Alignment for Reducing Hallucination in Decoder-Only TTS.

Focuses on Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speech.

Focuses on Post-Training Zero-Shot TTS for Fine-Grained Emotion and Duration Control via Natural Language.

Focuses on Deterministic Prompting for Speaker-Stable Low-Resource Greek TTS.

Focuses on Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue Synthesis.

Focuses on Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction.

Focuses on Ready to Speak: Aligning LLMs for TTS-Friendly Text Generation.

Focuses on Your Voice Cloning System is Secretly a Voice Anonymizer.

Focuses on X2Streaming-TTS: Causal Token-Level Text-to-Speech from Streaming Text with Speech-State Inheritance.

Focuses on Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions.

Focuses on Let Me Look at You: Advanced Facial Expression Modeling for Conversational Speech Synthesis.

Focuses on Zero-Shot Face-to-Speech Synthesis via Latent Space Adaptation of a Style-Diffusion TTS Model.

Focuses on Synthetic Speech, Real Signal: Paralinguistic Preservation and Cross-Lingual Augmentation via Voice Cloning.

Focuses on Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm.

Focuses on StellarTTS: Sparse Temporal Embedding for Low-Latency and Robust Speech Synthesis.

Focuses on Harness TTS: Towards Context-Aware Expressive Speech Synthesis with Harness Layer.

Focuses on AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis.

Our newest audio model introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.

Using OpenAI reasoning models, Descript unlocked automatic localization of large content libraries without losing timing or meaning.

Focuses on MOSS-TTS Technical Report.