Back to Toolbox
Fal.ai CSM-1B Text-to-Audio
Build multi-speaker scenes and let Fal’s CSM-1B voice each turn with crisp, conversational delivery.
Security heads-up: This playground sends your API key straight to Fal’s endpoint. For production, proxy the request server-side and keep keys out of the browser.
Configuration
Scene Turns
At least one turn is required. Each turn needs text and a speaker ID.Context Speakers (Optional)
Use prompt + audio pairs to steer voice matching for specific speakers.Configure API key, scene, and optional context, then click Generate.