AI Briefing#voice-cloning
The latest AI and developer news about #voice-cloning, with the original source and a short summary.
The latest AI and developer news about #voice-cloning, with the original source and a short summary.
Scenema Audio has been released as a ComfyUI native node that runs on 8GB VRAM.
The llama.cpp mainline now supports voice cloning with Qwen3-TTS 1.7B.
Fish Audio has launched S2.1 Pro, a high-performance voice model optimized for real-time conversation.
In a webinar, ElevenLabs revealed 7 key techniques for making AI voice agents sound as natural as humans.
ElevenLabs has recreated the voices of Hasbro's iconic characters, including Transformers and GI Joe, using AI and begun licensing them through the Iconic Marketplace.
Brazilian audio production company Fuzzr adopted ElevenLabs' Voice Cloning API to build a large-scale ad audio production pipeline.
ElevenLabs has launched the Vocals feature for ElevenMusic, enabling song generation with a consistent voice.
Newform is leveraging ElevenLabs' ElevenCreative to automate multilingual dubbing, audio restoration, and image generation for high-performing ads, maximizing content productivity.
Zyphra has launched ZONOS2, an open-source MoE-based TTS model capable of high-fidelity voice cloning and real-time inference.
ElevenLabs showcased AI voice restoration technology at SXSW London, enabling performances by artists who had lost their voices.
Through ElevenLabs' AI voice cloning technology, a patient who lost her voice has been able to continue her social role.
RedNote has released dots.tts, a SOTA TTS model with 2B parameters under the Apache 2.0 license.
Microsoft has launched MAI-Voice-2, a TTS model supporting 15 languages and voice cloning.
ElevenLabs has signed a deal with Stan Lee Universe to recreate the late creator's voice and likeness using AI.
A real-time TTS and voice cloning model supporting sub-60ms low latency and self-hosting has been released.
ElevenLabs has partnered with Stan Lee Universe to bring Stan Lee's voice, likeness, and music to its platform.
MOSS-TTS-v1.5 is a TTS model with improved multilingual synthesis performance and voice cloning stability.
Qwen has unveiled Qwen3.5-LiveTranslate, a real-time interpretation model that leverages visual context as well.
OpenAI acquired Weights.gg and shut down its unauthorized celebrity voice catalog.
Supertonic 3 has been released as an on-device TTS supporting 31 languages and emotion tags.
Resemble AI has unveiled DramaBox, a TTS that turns scene descriptions into acted-out speech and even applies watermarking.
Scenema Audio has released weights for a zero-shot, emotion-decoupled voice generation model.
Scenema Audio has released the weights and inference code for a voice generation model that separates emotion and speaker identity.
Resemble AI has released DramaBox, a voice synthesis model based on LTX 2.3.