Tag
The tweet highlights VoiceArena's evaluation method for voice models, which separates Task Completion and Naturalness via blind pairwise voting, and announces Jarvis Bench v0.5 as a conversational agent benchmark.
Fish Audio has raised $52 million in seed funding to develop AI voice models for creators and enterprises. The startup, which generates $21M in ARR and has 8 million users, offers open-source and paid voice generation models, including its latest S2.1 Pro API.
OpenAI announces GPT-Live, a new generation of voice models for natural human-AI interaction, rolling out in ChatGPT, and calls for design partners to test the API.
OpenAI announces GPT-Live, a new generation of voice models for natural human-AI interaction, rolling out in ChatGPT.
OpenAI released new full-duplex voice models GPT-Live-1 and GPT-Live-1 mini for more natural live conversations, allowing simultaneous speaking and listening, with improvements in turn-taking and context handling, and replacing Advanced Voice Mode in ChatGPT.
Flowcat addresses the high cost and limited context of realtime voice models, achieving 4x lower cost and 7x more context.
NielsRogge added a blog explaining the Moshi full-duplex voice model as a project page on Papers With Code, aiming to increase accessibility to the state-of-the-art architecture.
OpenAI has launched three new real-time audio models to enable continuous, multitasking voice interactions that prioritize long-context reasoning, live translation, and seamless tool use.