Content type of the request body.
Text to synthesize into speech. Max 1000 characters.
Voice preset ID. Determines the speaker voice used for synthesis. See the Kling documentation for available voice IDs and their supported languages.
Language of the selected voice. Must match the language supported by the chosen voice_id. Use an available service language code such as en.
Speech rate multiplier. Range 0.8–2.0 (one decimal place). Values outside this range are clamped automatically.
Success