🚨 AI News | TestingCatalog@testingcatalogFish Audio 发布 S2.1 Pro 生产级语音模型，支持多说话人对话、5 秒音频语音克隆及 MCP 智能体集成。该模型速度是 Cartesia 的 2 倍，成本仅为 Eleven Labs 的 1/6，并具备词级情感与语调控制能力。公司同期宣布完成 5200 万美元种子轮融资。
Fish Audio has released S2.1 Pro， its latest production voice model that is built for real-time conversational AI.
S2.1 Pro adds 👀 > Multi-speaker dialogue. > Voice cloning from short reference samples. > MCP plus agent-skill support for teams wiring speech into voice agents and long-form audio.
🚨 AI News | TestingCatalog@testingcatalog · XFish Audio 发布 S2.1 Pro 生产级语音模型，支持多说话人对话、5 秒音频语音克隆及 MCP 智能体集成。该模型速度是 Cartesia 的 2 倍，成本仅为 Eleven Labs 的 1/6，并具备词级情感与语调控制能力。公司同期宣布完成 5200 万美元种子轮融资。
Fish Audio has released S2.1 Pro， its latest production voice model that is built for real-time conversational AI.
S2.1 Pro adds 👀 > Multi-speaker dialogue. > Voice cloning from short reference samples. > MCP plus agent-skill support for teams wiring speech into voice agents and long-form audio.