DeepSeek App 能力开放至 API，含搜索、文件、语音等
DeepSeek 把自家 App 里的搜索、文件、语音这些能力全搬到 API 了，还有 OCR、ASR、TTS 独立接口和开源前端 Demo。想在自建应用里复刻一个 DeepSeek App 的开发者可以直接上手，不用再拼好几家服务。
DeepSeek 宣布将 DeepSeek App 背后的核心能力全面开放到 DeepSeek API，开发者可通过内置参数启用搜索、文件解析、链接读取、安全过滤和语音交互等功能。
除了在对话接口中一键启用这些内置能力，DeepSeek 还提供了独立的 OCR（图片文字识别）、ASR（语音识别）和 TTS（语音合成）API，可单独调用。官方同步发布了开源前端 Demo（cdn.deepseek.com/chat-demo），支持导入 DeepSeek 对话历史，代码托管在 GitHub，详细指南见 api-docs.deepseek.com。
此前这些功能仅存在于 DeepSeek App 内部，开发者想在自建应用中复现搜索问答或多模态交互需要自行拼装多家服务。现在用几个参数即可实现完整 App 体验，对构建中文智能客服、语音助手和文档问答应用的开发者来说，接入门槛和成本都明显降低。
🚀 The full DeepSeek App experience, now via API Search, files, links, safety, and voice. The capabilities behind the DeepSeek App are now available through the DeepSeek API. Enable built-in features with a few parameters, or call standalone APIs such as OCR, ASR, and TTS. Build richer conversations or recreate the full DeepSeek App in your own application. Try our open-source frontend demo, with support for importing DeepSeek conversation history. 🔗 Demo cdn.deepseek.com/chat-demo QK 📦 Cod github.com/deepseek-ai/ch… UgX 📖 Detai api-docs.deepseek.com/guides/build_a… M6Lk 1/4📊 88 ⚡
This report is categorized under AITOP's "Products" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include DeepSeek, API, 语音识别, OCR.
Source attribution: curated from 深度求索 DeepSeek (@deepseek_ai).
