2026-05-27
TechCrunch
7 related
ElevenLabs launches Music v2, which can switch genres mid-track and handle complex vocal compositions, built on licensed data and cleared for commercial use
Voice AI company ElevenLabs launched a new version of its music-generation model, called Music v2, that can switch genres mid-track.
2025-03-21
TechCrunch
12 related
OpenAI adds gpt-4o-mini-tts, a text-to-speech model that it says delivers more nuanced and realistic-sounding speech, and two speech-to-text models to its API
www.implicator.ai/claude-gets- ... tip @techmeme.com @fry69.dev : Unrelated to OpenAI, here is an interesting text to speech model/generator with supports “emotion” sounds like <laugh>, <chuckle>, <s...
2024-07-31
TechCrunch
38 related
OpenAI begins rolling out ChatGPT's Advanced Voice Mode, initially criticized for sounding like Scarlett Johansson during its demo in May 2024, to ChatGPT Plus
here are the most surprising examples so far Eddie Mitchell / CCN.com : Voice Theft in AI: The Dark Side of OpenAI's Advanced Voice Mode Marco Lancaster / Gizchina.com : ChatGPT Plus Advanced Voice Mo...
2024-03-31
TechCrunch
41 related
OpenAI debuts Voice Engine, which lets users generate synthetic copy of a voice from a 15-second sample, available to around 10 partners, including HeyGen
but Won't Release the Tech Yet Cade Metz / New York Times : OpenAI Unveils A.I. Technology That Recreates Human Voices Benj Edwards / Ars Technica : OpenAI holds back wide release of voice-cloning tec...
Loading articles...