Cohort of 43 admitted agents tagged capability:voice. Composite below is the cohort's average AgentScore.
| Cmp | Rank | Agent | 24h | Score | Δ24h | Watch |
|---|---|---|---|---|---|---|
| #32 | Meta: Muse Spark 1.2 saasMeta: Muse Spark 1.2: Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context... | 1 | 54.4 | +0.09 | ||
| #42 | Meta: Muse Wonder saasMeta: Muse Wonder: Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with... | 12 | 53.0 | +1.56 | ||
| #79 | Meta: Muse Spark 1.1 saasMeta: Muse Spark 1.1: Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context... | 4 | 48.8 | +0.23 | ||
| #36 | MoneyPrinterTurbo mitide-pluginMoneyPrinterTurbo: 利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow. | 3 | 48.6 | -0.19 | ||
| #208 | open-claude-ui mitopen-claude-ui: 基于 REA 深度拆解并高保真还原 Claude 官方桌面端 UI。纯手写 30 个独立 React 组件与 8 项硬核交互物理算法，附带 3000+ 行逆向分析手册。. | 4 | 34.5 | -0.10 | ||
| #212 | ChatTTS agplChatTTS: A generative speech model for daily dialogue. | 34.3 | +0.00 | |||
| #221 | hermes-gadget-sdk mithermes-gadget-sdk: Build small ESP32 voice gadgets for your own Hermes Agent: push-to-talk firmware, a desktop simulator and a Hermes platform plugin. | 7 | 34.1 | +0.21 | ||
| #291 | leon mitleon: ???? Leon is your open-source personal assistant. | 75 | 31.6 | -2.56 | ||
| #199 | Google: Gemini 3.1 Flash Lite saasGoogle: Gemini 3.1 Flash Lite: Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic... | 1 | 31.4 | -0.03 | ||
| #201 | Qwen: Qwen3.8 Omni Flash saasQwen: Qwen3.8 Omni Flash: Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,... | 2 | 31.2 | +0.13 | ||
| #342 | threejs-game-skills mitthreejs-game-skills: Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets. | 10 | 30.4 | +0.02 | ||
| #221 | Xiaomi: MiMo-V2-Omni saasXiaomi: MiMo-V2-Omni: MiMo-V2-Omni is a frontier omni-modal model that natively processes image, video, and audio inputs within a unified architecture. It combines strong multimodal perception with agentic capability - visual grounding, multi-step... | 111 | 29.8 | +6.00 | ||
| #383 | audio-studio-mcp mitmcp-serveraudio-studio-mcp: Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key. | 4 | 29.4 | +0.06 | ||
| #445 | no_ai_slop_writing_rules no_ai_slop_writing_rules: Claude Code reference: write in Louis Rossmann's voice, never like AI slop. Portable CLAUDE.md plus skills. | 9 | 28.4 | +0.01 | ||
| #253 | Mistral: Voxtral Small 24B 2507 saasMistral: Voxtral Small 24B 2507: Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio... | 28.2 | -0.05 | |||
| #465 | model:XiaomiMiMo/MiMo-V2.6-Flash-RL ide-pluginmodel:XiaomiMiMo/MiMo-V2.6-Flash-RL: discovered AI agent. | 12 | 28.0 | +0.04 | ||
| #477 | tamio mitmcp-servertamio: Native SSH client for macOS: Ghostty terminal, dual-pane SFTP, live server status, E2EE iCloud sync and an MCP server for agents. | 14 | 27.9 | 0.00 | ||
| #535 | Jarvis mitlibraryJarvis: An autonomous, local-first on-device AI agent and Android OS automation framework featuring full accessibility control, │ continuous voice intelligence, and self-evolving workflow execution. | 1185 | 27.2 | +10.18 | ||
| #552 | model:XiaomiMiMo/MiMo-V2.5 ide-pluginmodel:XiaomiMiMo/MiMo-V2.5: discovered AI agent. | 31 | 27.0 | -0.20 | ||
| #581 | jarvis_ai mitsaasjarvis_ai: Iron-Man-style voice assistant + holographic HUD for Hermes Agent. Local Whisper STT, ElevenLabs voice, agent-summoned media panels, runs on your own hardware. | 6 | 26.6 | +0.03 | ||
| #622 | khan-explainer mitide-pluginkhan-explainer: Claude Code skill: Khan Academy style explainer videos. A pen draws while a voice explains. Free, local, no API keys. | 11 | 26.2 | +0.04 | ||
| #305 | OpenAI: GPT Audio Mini saasOpenAI: GPT Audio Mini: A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million... | 1 | 25.8 | -0.02 | ||
| #695 | motion-video-skill mitide-pluginmotion-video-skill: Agent skill that produces beat-synced 1080p motion-graphic videos in HyperFrames (HTML + GSAP) with an AI voice-over, karaoke captions, SFX and generated music. MIT. | 25 | 25.6 | -0.04 | ||
| #318 | Perceptron: Perceptron Mk1.5 saasPerceptron: Perceptron Mk1.5: Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,... | 2 | 25.1 | +0.01 | ||
| #833 | model:XiaomiMiMo/MiMo-V2.6-Flash-MOPD ide-pluginmodel:XiaomiMiMo/MiMo-V2.6-Flash-MOPD: discovered AI agent. | 11 | 24.3 | +0.29 | ||
| #849 | arabic-ai-atlas mitmcp-serverarabic-ai-atlas: The Arabic AI ecosystem as a map, a list, and a skill your agent can install. | 2 | 24.1 | +0.13 | ||
| #1007 | the-muser mitthe-muser: The open-source alternative to Suno and ElevenLabs Music. Natural language music composition, run locally, own everything. | 12 | 22.8 | 0.00 | ||
| #1015 | memory-os mitide-pluginmemory-os: A 6-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider. | 12 | 22.7 | -0.00 | ||
| #1075 | hermes-plugin-gameforge mitclihermes-plugin-gameforge: Game development plugin for Hermes Agent: sound effects, music, NPC voices, pixel art, 3D models, Godot/Unity/Blender/Unreal, a playtester that actually plays the build, and one-click export. | 23 | 22.3 | -0.06 | ||
| #1172 | video-3d-kit ide-pluginvideo-3d-kit: Paste this link to your AI agent and say 'setup': it installs the /video-3d command for short voiced 3D character videos. | 91 | 21.5 | -0.72 | ||
| #1175 | tsov agpltsov: tsov (the shape of voice) — hum it, get a song you can keep editing. A local-first, AI-native music workspace: humming → transcription → arrangement → mixing → export, with humans and agents sharing one command layer. | 15 | 21.4 | +0.15 | ||
| #1285 | spring-ai-demos mcp-serverspring-ai-demos: Spring AI demos: OpenAI & Ollama chat, RAG with pgvector, image generation, text-to-speech, MCP server/client (Java 25, Spring Boot 4, Spring AI 2). | 20.5 | 0.00 | |||
| #1338 | xcode-mods mitmcp-serverxcode-mods: Xcode's build, tests, console and SwiftUI previews inside Claude Code. | 18 | 20.0 | 0.00 | ||
| #1455 | OpenAmika OpenAmika: OpenAmika: MekaHime's AI companion Amika, open source. Live2D avatar, real-time voice, long-term memory, OpenRouter or Ollama brain. | 121 | 19.1 | +0.96 | ||
| #1486 | hermes-voice mithermes-voice: Talk to a Hermes Agent profile through Home Assistant Assist. | 23 | 18.9 | +0.22 | ||
| #381 | Google: Gemini 3.1 Flash Lite (batch) saasGoogle: Gemini 3.1 Flash Lite (batch): Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic... | 2 | 18.0 | 0.00 | ||
| #387 | OpenAI: GPT Audio saasOpenAI: GPT Audio: The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced... | 24 | 17.6 | -2.11 | ||
| #1796 | qiaomu-app-review-insights mitide-pluginqiaomu-app-review-insights: 把 App Store 评价变成产品研究证据，发现痛点、机会和版本风险 | Turn App Store reviews into product research evidence: pain points, opportunities, and version risks. | 10 | 15.7 | +0.02 | ||
| #1819 | AutoTTS AutoTTS: The offical repo for "LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling". | 13 | 15.1 | 0.00 | ||
| #2131 | @transloadit/mcp-server mcp-server@transloadit/mcp-server: Transloadit MCP server. | 82 | 11.3 | +1.70 | ||
| #525 | OpenAI: GPT-4o Audio saasOpenAI: GPT-4o Audio: The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs... | 4.0 | +0.00 | |||
| #555 | Google: Gemma 3n 4B saasGoogle: Gemma 3n 4B: Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs???including text, visual data, and audio???enabling diverse tasks... | 1 | 2.9 | 0.00 | ||
| #607 | Google: Gemma 3n 4B (free) saasGoogle: Gemma 3n 4B (free): Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs???including text, visual data, and audio???enabling diverse tasks... | 0.8 | 0.00 |
Browse all sectors at /sectors.