AI Briefing#audio-ai
The latest AI and developer news about #audio-ai, with the original source and a short summary.
The latest AI and developer news about #audio-ai, with the original source and a short summary.
The model supports input sampling rates from 8 to 48 kHz and is designed to restore speech quality while preserving fidelity across diverse degradations.
The model operates as a true speech-to-speech system with inference speeds faster than real-time and runs locally on MacBook Pro M4 Max or higher.
The compact Mixture-of-Experts model supports speech recognition, audio reasoning, and optional synthesized speech responses in Chinese and English.
The model activates 6.5B parameters per inference step and supports speech recognition, audio reasoning, and synthesized speech responses under an MIT license.
FireRedTeam released FireRedAudio, a 9B parameter unified audio language model that decouples understanding and generation.
ASLP-lab has released MeanVC2, a real-time voice conversion model supporting cross-gender and cross-language conversion.
ElevenLabs has begun embedding inaudible digital watermarks into AI-generated audio using Google DeepMind's SynthID technology.
ElevenLabs has released the Finetunes Music API, enabling users to fine-tune music models with their own audio.
The Wan Team has released WanSong, a diffusion-based music generation model.
ElevenLabs is expanding the AI ecosystem by adding 173 research and engineering positions in California.
Zyphra has launched ZONOS2, an open-source MoE-based TTS model capable of high-fidelity voice cloning and real-time inference.
RedNote has released dots.tts, a SOTA TTS model with 2B parameters under the Apache 2.0 license.
LocalVQE, an ultra-compact audio model that removes real-time echo and noise using about 1 million parameters, has been released.
Anker has unveiled the **Thus** AI chip for audio devices.
44% of Deezer's daily uploads were tallied as AI-generated tracks.
Lovable has integrated with ElevenLabs, making it easy to build voice-based apps using various audio features such as TTS, STT, and music generation.
ElevenLabs officially launches in Korea, targeting the Korean market with its high-performance audio AI technology and agent platform.
ElevenLabs has launched **ElevenReader** with Polish language support, offering a library of Polish classic literature and AI voices of famous actors.
ElevenLabs unveiled new products including real-time Conversational AI and personalized podcast generation features, and announced market expansion into Poland and India.
ElevenLabs has signed a partnership with Reality Defender to strengthen audio deepfake detection technology.
This introduces the features and use cases of major AI voice generation tools, including ElevenLabs.
Google has unveiled Gemini 3.1 Flash Live, a high-quality audio and voice model with enhanced real-time conversation capabilities.
HuggingFace has released the FastRTC library, making it easy to develop real-time audio/video AI apps in Python.
Qwen's next-generation audio model, **Qwen2-Audio**, has been released, supporting both voice and text input.