Compare AI tools

	Leonardo.ai A	Cartesia S	Claude Code S	NotebookLM S
Tagline	Gamer + creator image gen with model fine-tuning built in.	Ultra-low-latency voice. Built for realtime agents.	Anthropic's CLI agent. Opus-powered, operates on your repo directly.	Google's research notebook. Turns your docs into a podcast.
Category	Image	Voice	Coding	Research
Pricing	Free + $12-$60/mo	Free tier + usage-based API	Part of Claude Pro/Max/Team plans	Free
Best for	Indie game devs, illustrators, anyone training custom style models.	Developers building voice agents, phone bots, interactive apps.	Developers who want an agent, not autocomplete. Large refactors, tests, docs.	Students, researchers, anyone with a stack of PDFs or a topic to learn.
Strengths	Train your own models on your style/character Great for game art + concept art Generous free tier	< 90ms latency — the fastest in the market Sonic model sounds natural Developer-friendly API	Runs locally, edits your actual files Strong on large codebases with 1M context Great at multi-step tasks	Upload anything, ask questions, get cited answers Audio Overview turns docs into a 10-min podcast Great for studying
Weaknesses	General output behind Midjourney Can be overwhelming	Fewer voices than ElevenLabs Less consumer-facing brand	Terminal-based — learning curve Can't be used without Claude subscription	Google-only Can be slow on large corpora
Kai's verdict	A-tier for creators training custom looks. B-tier for general use.	S-tier for realtime. If latency matters more than voice catalog, start here.	S-tier if you live in the terminal. Different shape than Cursor — complementary, not replacement.	S-tier for study. The Audio Overview is a killer feature. Try it with three of your favorite PDFs.
Link	Open →	Open →	Open →	Open →