Audio & Speech
Speech synthesis, transcription, music and voice agents. As of 2026-11-21, 549 indexed products match this subcategory (130 with full profiles); 325 were published in the last 90 days, against 118 in the 90 days before, roughly in step with the catalogue as a whole. By GitHub stars, AgentScope leads, holding 13% of the stars of the 404 products here with their own repository. The most common form is MCP servers (92% of indexed products).
SubcategorySegment label: Established DER
Segment statistics
Whole catalogue (all 549 indexed products, not only profiled ones). Calculated 2026-11-21.
Established. Mid-sized for its level, with launches roughly in step with the catalogue. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.058, attention is spread as if across about 17 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 503 | 91.6% | 85 |
| Agent skills | 22 | 4.0% | 22 |
| Frameworks | 12 | 2.2% | 12 |
| Plugins | 6 | 1.1% | 6 |
| Agent projects | 3 | 0.55% | 3 |
| Infrastructure | 2 | 0.36% | 2 |
| Rules packs | 1 | 0.18% | 0 |
4 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Speech to TextTranscribing audio into text. | 266 | 61 | 176 | Crowded |
| Text to SpeechTurning text into natural speech. | 210 | 57 | 106 | Crowded, slowing |
| Music & Sound GenerationGenerating music and sound effects. | 90 | 19 | 49 | Lagging the catalogue |
| Voice AgentsRealtime voice and phone agents. | 47 | 22 | 20 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (130 of 549), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | AgentScopePython multi-agent framework with message-based agent communication, tool use, memory and a visual studio for debugging. | Framework | Alibaba (AgentScope) | 36k | 1d ago | Apache-2.0 | ||
| 2 | MastraTypeScript framework for agents, workflows, RAG, memory and evals, with a local dev playground and deploy targets for common hosts. | Framework | Mastra | 30k | today | Apache-2.0 | ||
| 3 | Douyin_TikTok_Download_API🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API,支持 AI agent 通过 MCP 调用与离线语音转文字,Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up. | MCP server | Evil0ctal | 22k | 1d ago | Apache-2.0 | ||
| 4 | ConcatBeta: The truly free, open-source, local-first, cross-platform video editor. Scriptable through a JSON-RPC API & MCP. | MCP server | jub0t | 19k | 1d ago | AGPL-3.0 | ||
| 5 | lemo-opuscarA toolbox of film styles made in code for Claude Code: 99 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱:99 种现成风格,也能做出你自己的 | Agent skill | lemomo-ai | 19k | 1d ago | — | ||
| 6 | PipecatPython framework for voice and multimodal conversational agents built as pipelines of streaming speech, LLM and TTS services. | Framework | Daily | 17k | today | BSD-2-Clause | ||
| 7 | LiveKit AgentsFramework for realtime voice and video agents that join LiveKit rooms, with turn detection and pluggable speech, LLM and TTS providers. | Framework | LiveKit | 15k | today | Apache-2.0 | ||
| 8 | OpenCreatorFormerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc. | Agent skill | krillinai | 14k | 1d ago | Apache-2.0 | ||
| 9 | VoltAgentTypeScript agent framework with memory, workflows, supervisor/sub-agent patterns and a companion observability console. | Framework | VoltAgent | 11k | 15d ago | MIT | ||
| 10 | ffmpeg-skillLocal FFmpeg video and audio tools over stdio. Footage stays on this machine. | MCP server | kajisho5 | 9.1k | today | MIT | ||
| 11 | AgentsQuickly build text, voice and video agents. Fast, Go based Agent backend with SDKs for every language. Sensible defaults for search, knowledge, skills, telephony, sandboxes, memory and persistence. Sovereign AI. Take control of your AI. | Agent project | GetStream | 8.2k | today | Apache-2.0 | ||
| 12 | ODSODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server. | Agent project | Osmantic | 7.9k | 2d ago | Apache-2.0 | ||
| 13 | OpenScreenScreen recorder and video editor. Agents record, trim, zoom, caption, add effects and export. | MCP server | getopenscreen | 7.7k | today | MIT | ||
| 14 | vapi-networkBuyer-controlled client for x402 API payments in USDC on Base. | MCP server | vAPI-Network | 5.4k | 1d ago | Apache-2.0 | ||
| 15 | earshotSound effects for coding agents: ask in plain words and earshot renders the sound in code. CPU-only, no audio model, open source. | Agent project | Leonxlnx | 5.4k | 1d ago | MIT | ||
| 16 | Handsy AILet AI agents see and operate a real iPhone via an ESP32-S3 USB HID + AirPlay. No jailbreak. | MCP server | onehumanbeing | 5.2k | today | MIT | ||
| 17 | py-xiaozhiOpen-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction. | MCP server | huangjunsen0406 | 3.6k | 12d ago | MIT | ||
| 18 | anything2explainerTopic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion. | Agent skill | Vincentwei1021 | 3.5k | 2d ago | — | ||
| 19 | natively-cluely-ai-assistantNatively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Interview Coder. Real-time transcription, AI meeting notes, lecture recording, local RAG, BYOK, and stealth mode. Runs locally. No subscriptions. No data breaches. | Agent skill | Natively-AI-assistant | 3.4k | today | — | ||
| 20 | VexaMeeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled. | MCP server | vexa.ai | 3.0k | 8d ago | Apache-2.0 | ||
| 21 | claude-code-video-toolkitMake videos with Claude Code: script, AI voiceover, music, video clips and render, on open-source models that cost cents | Agent skill | digitalsamba | 2.7k | 1d ago | MIT | ||
| 22 | claude-real-videoLet any LLM watch a video locally — and search everything it has ever watched. | MCP server | HUANGCHIHHUNGLeo | 2.3k | 1d ago | MIT | ||
| 23 | pokiPoki uses your iPhone like you do. An open-source agent app that runs on your iPhone, reads the screen, and taps, types and swipes in real apps with your own model account. | MCP server | JosssphZhou | 1.7k | today | AGPL-3.0 | ||
| 24 | ava-whatsapp-agent-courseMeet Ava, the WhatsApp Agent | Infrastructure | neural-maze | 1.7k | 1y ago | MIT | ||
| 25 | minutesThe private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting. | MCP server | silverstein | 1.6k | today | MIT | ||
| 26 | MiniMax-MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs. | MCP server | MiniMax-AI | 1.6k | 11d ago | MIT | ||
| 27 | claude-video-visionGive Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis | MCP server | jordanrendric | 1.5k | 1mo ago | MIT | ||
| 28 | voicemodeNatural voice conversations for AI assistants - STT/TTS via MCP | MCP server | voicemode.dev | 1.5k | 1d ago | MIT | ||
| 29 | xiaozhi-esp32-server-java小智ESP32的Java企业级管理平台,提供设备监控、音色定制、角色切换和对话记录管理的前后端及服务端一体化解决方案 | MCP server | joey-zhou | 1.4k | 3d ago | MIT | ||
| 30 | chubbyskills把中文全渠道内容(抖音 / B站 / 小红书 / 公众号 / X / 播客)采集进个人知识库的 14 个 AI Skill:图文存图、视频转文字稿、字幕优先免 GPU、RSS/YouTube 订阅调度与每日情报简报,附带知识库 MCP server。| Ingest Chinese content into your personal knowledge base — image/video routing, subtitle-first transcription, feed subscriptions with daily digests, and a KB MCP server. | Agent skill | chubbyguan | 1.3k | 1mo ago | MIT | ||
| 31 | PhoneClawPhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference. | Framework | kellyvv | 1.3k | 3mo ago | Apache-2.0 | ||
| 32 | ChatCutAI video editor for agents: cut footage, add captions and motion graphics, export editable edits. | MCP server | chatcut.io | 1.1k | 3d ago | Apache-2.0 | ||
| 33 | anymdAny file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP. | MCP server | SylphxAI | 1.1k | today | MIT | ||
| 34 | CitraCitra — PDF answers with page-level proof: structure, tables, OCR, and page citations. | MCP server | SylphxAI | 1.1k | today | MIT | ||
| 35 | PDF Reader MCPEvidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence. | MCP server | SylphxAI | 1.1k | today | MIT | ||
| 36 | BoxThe most advanced, fully offline client-side AI suite on Android today. | MCP server | jegly | 1.0k | today | — | ||
| 37 | ai-video-editorOpen-source, local-first video editor where creators and AI agents edit the same real timeline. | Agent skill | MartinDelophy | 1.0k | 3d ago | MIT | ||
| 38 | voice-aiRapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability. | Framework | rapidaai | 760 | 2d ago | — | ||
| 39 | claudemyClaudemy: an open-source alternative to Udemy and Coursera. Give Claude a topic, it researches the web and builds a course of 2-minute audio lessons with cited sources. A free Claude Code skill. | Plugin | assafkip | 713 | 23d ago | MIT | ||
| 40 | Audio StudioLocal AI BGM and sound effects with Stable Audio 3 (Apple Silicon MLX, NVIDIA CUDA) | MCP server | kanaworksai-hue | 696 | 5d ago | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| YouTube | 24 | 4.4% |
| 3 | 0.5% | |
| Android | 2 | 0.4% |
| Solana | 2 | 0.4% |
| Stripe | 2 | 0.4% |
| Discord | 1 | 0.2% |
| Docker | 1 | 0.2% |
| GitHub | 1 | 0.2% |
| Godot | 1 | 0.2% |
| Google Ads | 1 | 0.2% |
| Google Workspace | 1 | 0.2% |
| 1 | 0.2% | |
| PostgreSQL | 1 | 0.2% |
| 1 | 0.2% | |
| Slack | 1 | 0.2% |
Launches per month
New Audio & Speech products per monthSRC
Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-11 | 2 |
| 2024-12 | 2 |
| 2025-02 | 2 |
| 2025-04 | 2 |
| 2025-05 | 1 |
| 2025-08 | 2 |
| 2025-09 | 4 |
| 2025-10 | 2 |
| 2025-12 | 2 |
| 2026-01 | 6 |
| 2026-02 | 9 |
| 2026-03 | 15 |
| 2026-04 | 21 |
| 2026-05 | 27 |
| 2026-06 | 39 |
| 2026-07 | 36 |
| 2026-08 | 53 |
| 2026-09 | 52 |
| 2026-10 | 155 |
| 2026-11 | 104 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
No scored opportunity here
Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .