Multimodal generative AI resources : talking heads, STT, TTS, image & video generation, and AI Agent
Awesome Generative AI Resources
An opinionated, builder-first map of the generative AI stack
Why This List | Start Here | Top Picks | Build Paths | Resource Index | Contributing
Why This List
Most AI awesome lists are too broad, too stale, or too academic.
This repo is for builders who want to ship real products with modern generative AI:
- Practical entry points across agents, MCP, speech, vision, and model APIs
- Curated links that are useful for implementation, not just hype
- Faster path selection instead of endless scrolling through generic lists
Start Here
Pick one path and get moving in under 10 minutes:
- Build AI agents: AI Agents
- Build speech products: STT Models, TTS Models
- Build visual products: Text-to-Image, Talking Head
- Build model apps: Transformers, GenAI APIs
- Add tool integration: MCP Servers
Top Picks
If you only open a few sections, start with these:
| Area | Best Starting Point | Why It Matters | |:---|:---|:---| | Agentic apps | AI Agents | Frameworks, coding agents, memory systems, and orchestration tools | | Tool-using LLMs | MCP Servers | Quick map of the MCP ecosystem and the most useful server categories | | Voice AI | TTS Models, STT Models | Core stack for assistants, call automation, and speech UX | | Visual generation | Text-to-Image, Talking Head | Useful for multimodal products, synthetic media, and creator tools | | Model integration | GenAI APIs, Transformers | Compare hosted APIs and open model tooling quickly |
Build Paths
1. Agentic Apps
- Start: AI Agents
- Add memory and context: context-engineering.md
- Add tool integration: mcp.md
- Best for: coding agents, assistants, workflow automation, and multi-agent systems
2. Voice and Audio Products
- CharaVox - AI voice generation platform with character voices, voice cloning, and studio-quality TTS in 6 languages (en/zh/ja/ko/es/pt). Powered by VoxCPM.
- Speech recognition: stt-models.md, stt-datasets.md
- Speech synthesis: tts.md, voice-cloning.md
- Emotion and affect: emotion-recognition.md
- Best for: call agents, speech interfaces, dubbing, and voice cloning pipelines
3. Vision and Video Products
- Image generation: text-to-image.md
- Talking avatars: talking-head.md
- Best for: creative tools, avatars, media generation, and synthetic presenters
4. Foundation Model Productization
- Model selection: transformers.md
- API integrations: genai-apis.md
- Best for: choosing between open-source models, APIs, and deployment approaches
Resource Index
| Area | Primary Files | |:---|:---| | Agents and orchestration | ai-agents.md, mcp.md, context-engineering.md | | Speech | stt-models.md, stt-datasets.md, tts.md, voice-cloning.md, emotion-recognition.md | | Vision and media | text-to-image.md, talking-head.md | | Models and APIs | transformers.md, genai-apis.md | | Extended references | more_detailed.md |
Quality Notes
- Curated manually for practical relevance and builder usefulness
- Focused on tools, repos, datasets, and frameworks with real implementation value
- Some files include star counts from periodic updates
- If you spot stale entries, weak categorization, or broken links, open an issue or PR
Contributing
Contributions are welcome for:
- New high-quality open-source repos
- Broken links or outdated entries
- Better categorization and structure
Disclaimer
This is a curated collection of external resources. Rights and credit belong to each original author and organization.
