Generate Speech (Text-to-Speech)

Transform text input into single-speaker or multi-speaker audio using native text-to-speech (TTS) generation capabilities. TTS is controllable through natural language to guide style, accent, pace, and tone of the audio. **Capabilities:** - Single-speaker or multi-speaker audio (up to 2 speakers) - 30 voice options with different characteristics (bright, upbeat, informative, etc.) - 24 supported languages with automatic language detection - Controllable style, tone, accent, and pace via pr...