Pipecat 1.16 新增 PerceptionReader，配合 Google Decision 1 识别语音语气
语音机器人一直听不出用户的讽刺和情绪，Pipecat 1.16 的 PerceptionReader 直接补上了这块，把音频流给 Google Decision 1 就能读出语气。做 voice agent 的开发者可以直接去他们的 Vercel demo 上试玩，对比自己现在的 ASR+LLM 流水线，文档也更新好了。
Pipecat 发布 1.16 版本，新增 PerceptionReader 组件，Daily 的 Phil Schmid 在 X 上分享了配合 Google Decision 1（昨日发布）的实测示例，并上线了公开 demo（pecat-google-decision-demo.vercel.app）。
语音智能体此前大多只能理解用户说了什么，却无法捕捉说话方式。PerceptionReader 的思路是把音频流直接喂给 Google Decision 1，模型会返回对用户语气（prosody）、语调和讽刺语气的较为准确的判读。Schmid 强调“怎么说”和“说什么”同样重要，这正是现有 voice agent 缺失的能力。
团队还在探索多种衡量表现力的方法，后续会有更多分享。对做语音智能体的开发者来说，Pipecat 文档（docs.pipecat.ai）已同步更新 PerceptionReader 的 API 参考。
Great example for the Google Decision 1 audio capability. Jon Taylor @JonPTaylor Pipecat 1.16 adds PerceptionReader, something I'm really excited about. How someone speaks can matter just as much as what they say, and voice agents have mostly been missing that. We’ve been testing it with Google Decision 1, released yesterday. Stream it audio and you get a pretty accurate read on the prosody, tone and sarcasm of what the user said. Try talking to it at this demo here: …pecat-google-decision-demo.vercel.app We've exploring many different ways of measuring expressivity... more to share on that soon! ➡️ Pipecat Docs: docs.pipecat.ai/api-reference/… ➡️ Google Decision 1: blog.google/innovation-and…
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Pipecat, Google Decision 1, PerceptionReader, 语音识别.
Source attribution: curated from Philipp Schmid (@_philschmid).
