搜索结果

AIprm

Summary: AIPRM is a prompt management tool and community-driven prompt library for generative AI.

Capsolver

Summary: CapSolver is an AI-powered captcha solving service that supports multiple types of captchas.

Typecast AI

Typecast is an AI voice generator with 400+ realistic voices for creating lifelike audio content.

sorisori.ai

AI content creation hub for transforming ideas into custom content.

SDXL Turbo Playground

Ultra-fast, high-quality AI image generation using ADD technology.

Humata AI

Humata is an AI tool that quickly answers questions about data.

anakin.ai

AI platform for generating content and automating workflows.

SpeechGen.io

Generate high-quality voiceovers with SpeechGen.io's realistic Text-to-Speech AI technology.

summarizer.org

Free summary generator for any text.

MicVoice.Ai

AI voice generator for realistic text-to-speech conversion.

Voicemaker

Voicemaker® converts text to human-like voices, offering various voice profiles and customization options.

fish-speech-mcp

An MCP server for text-to-speech synthesis (TTS) for LLMs.

HubSpot MCP Server

MCP server for integrating with HubSpot CRM, allowing seamless creation, retrieval, and management of summary records as Note engagements, all linked to a dedicated shared contact record.

Summary

PoC: MCP Server using OpenAPI specs to generate tools

HubSpot MCP Server

Repository Name: hubspot-mcp-summary Repository Description: A Model Context Protocol (MCP) server for managing shared summaries in HubSpot. This project integrates with HubSpot's CRM to create, updat

Voicevox MCP Server

Asr_mcp_server

A Model Context Protocol (MCP) server that provides ASR(Automatic Speech Recognition) capabilities using the whisper engine. This server exposes TTS functionality through MCP tools, making it easy to

Webpage Summary Agent with mcp-agent and qwen

Webpage Summary Agent with mcp-agent 、MCP servers and qwen.

Spark-TTS

<p>Overview Spark-TTS 是由出门问问（Mobvoi）联合多所顶尖学术机构（如香港科技大学、上海交通大学）最新推出的新一代语音合成模型，其核心创新在于BiCodec编码技术和与文本大模型的结构统一性，利用大型语言模型 (LLM) 的强大功能实现高度准确且自然的语音合成。</p> <p>Spark-TTS is an advanced text

Scenethesis

Scenethesis 是 NVIDIA 推出的创新框架，用在从文本生成交互式 3D 场景。框架结合大型语言模型（LLM）和视觉感知技术，基于多阶段流程实现高效生成，用 LLM 进行粗略布局规划，基于视觉模块细化布局生成图像指导，用优化模块调整物体姿态确保物理合理性，基于判断模块验证场景的空间连贯性。Scenethesis 能生成多样化的室内外场景，具有高度的真实感和物理合理性，广泛应用在虚拟内容

Code Researcher

Code Researcher是微软研究院推出的深度研究Agent工具，专门用于处理大型系统代码库及其提交历史，自动化修复系统代码崩溃问题。通过三个阶段工作：分析（Analysis）、合成（Synthesis）和验证（Validation）。在分析阶段，Code Researcher基于多步推理策略，结合代码语义、模式和提交历史信息，收集上下文并存储在结构化内存中。合成阶段基于收集到的上下文生成修

MultiAgentPPT

MultiAgentPPT 是多智能体演示文稿生成系统，基于 A2A（Ask-to-Answer）、MCP（Multi-agent Control Protocol）和 ADK（Agent Development Kit）架构。MultiAgentPPT 基于多Agent协作和流式并发机制，从用户输入的主题自动生成高质量的 PPT 内容。系统包括大纲生成、主题拆分、并行调研和内容汇总等步骤，具备多