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.
The 4-bit version requires only 4 GB of VRAM and achieves approximately 13x real-time speed on an RTX 5090.
Loudness and age tags significantly influence listener preference, while usage metrics and professional status show no correlation with quality.
A guide explains how content creators can use ElevenLabs' voice cloning tools, including Eleven v4 and ElevenCreative, to produce multilingual and consistent content.
The model supports 43 languages and runs on phones, laptops, and browsers using Apache 2.0 licensed weights.
The guide outlines the three-step process of voice synthesis, distinguishes between instant and professional cloning, and details detection methods for AI-generated audio.
The guide distinguishes voice over from dubbing and acting, and outlines a five-step process for generating audio using ElevenCreative Studio.
The 1.7B parameter model supports zero-shot voice cloning in 20+ languages and expressive emphasis control without requiring a GPU.
The 0.5B parameter model supports voice design, 7 languages, and emotion/style control.
The new English models support voice cloning and are designed to run on CPU, allowing GPUs to remain dedicated to LLM inference.
Baroness Campbell used an ElevenLabs voice clone to address the House of Lords on Personal Health Budgets, marking the first time a peer has used AI-generated audio in Parliament.
The update reduces voice roughness and break-up while maintaining ~300 ms first-audio latency on laptop CPUs.
It converts English, Japanese, and Chinese podcasts into Korean while preserving the original speaker's tone, offering an 80% credit discount for already dubbed content.
The new leaderboard uses objective metrics like WER and RTFx to evaluate open-source TTS models, reducing assessment time from weeks to hours.
Eleven v4 Turbo achieves a median inference latency of ~100ms, enabling low-latency conversational agents.
It achieved first place overall in the Hume AI benchmark and offers a library of over 2,000 production-ready voices.
The open-source local TTS 'LoudKit', supporting voice cloning and 10 languages, has been released.
VoiceStudio, an open-source tool for performing voice cloning, video dubbing, and transcription locally, has been released.
ElevenLabs is expanding its $1 billion '1 Million Voices' initiative to Brazil, providing voice restoration technology through local partnerships.
Halo NeuroAI has released Sopro V2 Turbo, a 120M-parameter open-source voice cloning model that natively supports European Portuguese and enables real-time streaming on laptop CPUs.
The 120-million-parameter open-source TTS model Sopro V2 delivers SOTA-level voice cloning performance and enables fast inference even on CPUs.
Voice cloning is divided into speed-focused **Instant Voice Cloning (IVC)** and precision-focused **Professional Voice Cloning (PVC)**.
Voice cloning APIs generate multilingual synthetic speech using the voice of a specific individual.
The AI Dubbing API generates multilingual audio while preserving the original emotion and timing.
ElevenLabs released the Dubbing v2 API, which preserves emotion and synchronization across more than 90 languages.