Tag
Ant 发布了开源音频模型家族 Ming-3.0 Audio，采用 MIT 许可并开放权重与代码，支持语音与文本混合输入并可输出文字或语音回复，提供 126B 总参数的 Flash 和 9.3B 总参数的 tiny 两个 MoE 检查点。
AI music platform Suno is launching Speech, a public beta feature that generates spoken voices from scripts or prompts alongside synchronized background music as a single cohesive audio track.
The paper presents StepAudio3Realtime, an audio-language foundation model for real-time spoken interaction, using a continuous listen-converse-think-act loop with Think-While-Speaking to achieve deep reasoning and low latency, with top-tier performance on benchmarks like MMSU and Full-Duplex Bench.
The developer announces plans to accelerate the LFM2.5-Audio-1.5B model using reinforcement learning methods and synthetic data, with a focus on English, and shares optimizations for the Mimi codec model to improve speed and quality for open-source release.
Vercel announces that Google's Gemini 3.5 Transcribe model is now available on AI Gateway, supporting live and recorded audio transcription in over 85 languages with automatic language detection and custom vocabulary.
Fish Audio S2 is a new open-weight audio model available on Hugging Face, offering two models for timing and acoustic details, with fast inference and a hosted version S2.1 Pro supporting 83 languages at lower cost than ElevenLabs.
Dia is a 1.6B-parameter open-source text-to-speech model that generates English dialogue from transcripts, supporting two-speaker generation, audio conditioning, and nonverbal cues.
Released a model (Stereo2Spatial) that converts stereo music tracks to spatialized binaural mixes, using flow-matching diffusion and amplitude lifting for stable training. The model and a Windows app are open-sourced under Apache 2.0.
OpenAI is rolling out a new bidirectional voice model (Bidi 1) for ChatGPT that allows simultaneous speaking, hearing, and listening, real-time translation, and improved conversation context handling. The upgrade is appearing in the web interface and app for some users, with a broader release expected soon.
OpenAI is preparing to release GPT-Bidi-1, a next-generation voice model for ChatGPT that supports bidirectional communication, interruptions, and mid-sentence adjustments, aiming to close the gap between voice and text capabilities.
Gemini 3.5 Live Translate is a new audio model for real-time speech-to-speech translation.
Google releases Gemini 3.5 Live Translate, an audio model for near real-time speech-to-speech translation in over 70 languages, preserving speaker intonation and pacing. It is rolling out across Google products including the Gemini Live API, Google Meet, and Google Translate.
Google has released Gemini 3.1 Flash Live, a new high-quality audio model designed for more natural and reliable real-time voice interactions with improved latency and reasoning capabilities.