Explore complete, runnable examples from our cookbook repository.
Generate speech in 5 lines of code — the simplest way to start.
Real-time audio streaming with latency metrics and chunk-by-chunk playback.
List, filter, and preview 80+ voices by language, gender, and accent.
Custom pronunciations for brand names, acronyms, and technical terms.
Give it a topic, get a two-host AI podcast with LLM-generated script.
Convert any text file into a narrated, chaptered audiobook.
Web app to browse and preview all voices — deploy to Vercel.
Translate text between 40+ languages with TTS and STT.
Browse all examples on our GitHub repository.