Pika这次把音频模型价格打到市面最低，四款模型覆盖配乐、音乐、音效和语音，做内容的朋友可以留意下。
Pika推出音频模型系列，涵盖Soundtrack、Music、SFX和Speech四种生成式声音模型，覆盖声音创作全谱系。官方称其推理技术使这些模型比市场上其他音频模型便宜最多20倍。Pika已在官网博客发布技术详解，介绍高效推理方法如何实现规模化下的音频质量。
We built Pika Audio Models around a simple engineering challenge: make frontier audio quality more a...
We built Pika Audio Models around a simple engineering challenge: make frontier audio quality more accessible at scale. Our team's efficient inference techniques made Soundtrack, Music, SFX, and Speech up to 20× more cost-efficient than other audio models. Read the technical overview → experiment.pika.art/blog/pika-audi… Pika @pika_labs Sound on! Today, we’re introducing Pika Audio models: 4 frontier foundation models that cover the full spectrum of generative sound. And we’ve made them less expensive than every audio model on the market—up to 20x times cheaper.* *There is literally no disclaimer Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 3 🔄 1 ❤️ 6 👀 1008 📊 3 ⚡