The Rime CLI: From zero to AI voices in seconds
Mar 17, 2026
The Rime CLI lets you synthesize speech, preview voices, and generate production-ready API calls directly from your terminal. No dashboard. No context switching. Just your keyboard and 94+ voices that don't sound like robots.
Why a CLI?
The best voice experiences get built by developers who can iterate fast. Switching to a browser to test a voice, copy a curl command, or verify output format slows that loop down. The CLI closes it. You can go from install to audio in under 60 seconds, and stay in flow while you build.
It also fits naturally into the way AI-assisted development is evolving. If you're using Claude Code, you can invoke rime tts directly from your agentic workflow, previewing voices, generating test audio, or scaffolding API calls without ever breaking out of your coding session.
Getting Started
Install
Verify it worked:
Log in
This opens your browser once to authenticate. The CLI saves your API key to ~/.rime/rime.toml automatically — you won't need to touch it again.
Hear your first voice
That's it. You're talking to Rime.
Synthesize your own text
Want to save the output instead of playing it back?
Play it back with waveform visualization:
Try different voices
Swap the --speaker flag to explore voices. We have 94+:
Generate a curl command for API integration
When you're ready to wire Rime into your app, generate a ready-to-use curl command:
The CLI outputs a complete, runnable curl call with your auth header. Add --show-key to include your actual API key, or --oneline for easy copy-paste into scripts.
What's next
The CLI is the fastest path to production-ready voice. Check out the full CLI reference for all commands and flags, browse the voice library, and compare Arcana and Mist v2 to choose the right model for your use case.