覆盖 459 类工作流,通过流量估算、产品功能与替代方案辅助选型。
“JavaScript AI framework” · 语音合成与转换·27 个结果
重新开始
面向后端 API 与自动化的 AI 可视化工作流构建器

LocalMode UI is an open-source shadcn registry of copy-owned, composable AI interface components plus installable blocks that run real models directly in the browser. It ships 100+ React components and 36 blocks covering chat, RAG knowledge bases, vision, audio, photo editing, agents and privacy tooling, all designed to be local-first by default and cloud-compatible when you want it.
LocalMode UI is an open-source shadcn registry of copy-owned, composable AI interface components plus installable blocks that run real models directly in the browser. It ships 100+ React components and 36 blocks covering chat, RAG knowledge bases, vision, audio, photo editing, agents and privacy tooling, all designed to be local-first by default and cloud-compatible when you want it.

面向 1000+ 语言、低代码且模型无关的 AI 智能体与工作流平台


十天交付可用系统的 AI 咨询与落地服务

以 1500+ 模型驱动内容与 AI 产品的无代码平台

实时起草临床病历的环境式 AI 医疗书记


为每项任务挑选最佳模型,构建定制企业 AI 自动化

一站式 AI 数字人与多模态内容生产平台

Vocode is an open-source framework and developer API for building voice agents that can talk on the phone, in the browser or inside a meeting. It bundles speech-to-text, text-to-speech, LLM orchestration and telephony integrations behind one set of Python and TypeScript abstractions.
Vocode is an open-source framework and developer API for building voice agents that can talk on the phone, in the browser or inside a meeting. It bundles speech-to-text, text-to-speech, LLM orchestration and telephony integrations behind one set of Python and TypeScript abstractions.


用 AI 记忆、整理并查询你的知识
AI 驱动的面试与候选人筛选工具包

Visnet is an AI research and engineering company behind the VISNET Framework, a headless, multi-compatible neural-network interface that packages deep-vision and language models behind a single gateway. Teams use it for facial feature recognition, autonomous drone structural inspection, live multilingual audio transcription and license plate recognition.
Visnet is an AI research and engineering company behind the VISNET Framework, a headless, multi-compatible neural-network interface that packages deep-vision and language models behind a single gateway. Teams use it for facial feature recognition, autonomous drone structural inspection, live multilingual audio transcription and license plate recognition.

Zookish is an embeddable conversational AI assistant that adds chat and voice interactions to any website with a single line of code. It pairs an on-page AI widget with conversational memory and a knowledge base you control, so visitors can ask questions by typing or speaking and get answers grounded in your own content. A lightweight install and dashboard-based branding let teams launch a voice user interface without custom development.
Zookish is an embeddable conversational AI assistant that adds chat and voice interactions to any website with a single line of code. It pairs an on-page AI widget with conversational memory and a knowledge base you control, so visitors can ask questions by typing or speaking and get answers grounded in your own content. A lightweight install and dashboard-based branding let teams launch a voice user interface without custom development.

由全球分布式工程团队提供定制 AI 开发、聊天机器人与咨询服务

PPTalker is an AI-powered converter that turns PowerPoint decks, PDF documents and HTML slide frameworks such as Slidev and reveal.js into professional videos. It generates an AI voiceover, auto-writes speaker notes from your slides, and adds multilingual subtitles so a presentation can be published as watchable video without a recording studio.
PPTalker is an AI-powered converter that turns PowerPoint decks, PDF documents and HTML slide frameworks such as Slidev and reveal.js into professional videos. It generates an AI voiceover, auto-writes speaker notes from your slides, and adds multilingual subtitles so a presentation can be published as watchable video without a recording studio.

Speechllect is a speech technology platform offering real-time speech-to-text and text-to-speech based on its own Sense Theory approach to modeling speech meaning.
Speechllect is a speech technology platform offering real-time speech-to-text and text-to-speech based on its own Sense Theory approach to modeling speech meaning.