Winvest — Bitcoin investment
audio generation AI News List | Blockchain.News
AI News List

List of AI News about audio generation

Time Details
12:15
PixVerse V6 Video Gen Breakthrough: Multicut Editing and Audio Support Boost Character Consistency — Analysis and Creative Workflow Tips

According to PixVerse on X, PixVerse V6 is now available with multicut video editing and audio generation, enabling higher-quality action scenes and more controllable storytelling (source: PixVerse, Mar 31, 2026). According to creator Towya on X, using a character sheet as the opening reference frame in PixVerse V6 significantly improves character consistency across cuts, addressing a common failure mode in video diffusion pipelines (source: @towya_aillust post referenced by PixVerse). As reported by PixVerse, the new release supports multi-shot sequencing, which reduces identity drift between clips and strengthens narrative continuity for branded content, anime-style shorts, and UGC ads (source: PixVerse on X). According to Towya, V6 delivered strong action performance without separate per-shot references, suggesting lower prompt and reference overhead for creators and studios adopting a template-first workflow (source: @towya_aillust on X).

Source
2025-10-15
19:49
Veo 3.1 AI Model Launches on Krea with Image References, Frame Interpolation, and Enhanced Audio Generation

According to @krea_ai, the newly released Veo 3.1 AI model on the Krea platform introduces advanced features such as support for image references, frame interpolation capabilities, and significantly improved audio generation. These upgrades enable creators and businesses to produce higher-quality multimedia content more efficiently. Krea is also offering a 75% discount for all Pro and Max users to encourage adoption of these new AI-powered creative tools. This update demonstrates Krea's commitment to expanding AI-driven content generation for professional and commercial applications, opening up new market opportunities in video, design, and audio production (source: @krea_ai, Oct 15, 2025).

Source
2025-08-20
17:29
ElevenLabs v3 Dominates Audio Generation: Poe Platform Integrates AI Text-to-Speech for Enhanced User Experience

According to @elevenlabsio, ElevenLabs’ audio generation models remain the most utilized on Quora’s Poe platform, with the recent integration of ElevenLabs v3 powering Poe’s speak button to convert text responses into high-quality audio (source: @elevenlabsio). This partnership demonstrates the rising demand for AI-driven text-to-speech solutions, offering scalable opportunities for content creators, edtech providers, and customer service platforms seeking seamless, natural-sounding audio generation. The adoption of ElevenLabs v3 on a high-traffic platform like Poe signals continued growth and mainstream acceptance of advanced AI audio technologies, opening new market avenues for enterprises looking to enhance accessibility and user engagement.

Source