Base text-to-speech API paid via x402. Converts text input into a hosted audio U...

{ "bodyFields": { "action": { "description": "Optional action. Omit for TTS. Use 'list' to list available voices instead of generating speech.", "enum": [ "list" ], "required": false, "type": "string" }, "text": { "description": "Text to convert to speech when action is omitted (TTS mode). Required for paid TTS calls.", "required": false, "type": "string" }, "voice_id": { "description": "Optional ElevenLabs voice_id. If omitted, a default narrator voice is used.", "required": false, "type": "string" } }, "bodyType": "json", "method": "POST", "type": "http" }

{ "action": { "description": "Action performed: 'tts' for text-to-speech, 'list' for voice listing.", "type": "string" }, "chars": { "description": "Number of characters used for pricing in TTS calls.", "type": "number" }, "ok": { "description": "True on success", "type": "boolean" }, "price_usdc": { "description": "Price charged for this call in USDC (6 decimals, rounded up). Minimum is 0.001 USDC.", "type": "number" }, "tts_url": { "description": "Public URL of the generated audio file hosted on ImageKit (TTS only).", "type": "string" }, "voice_id": { "description": "Voice ID used for the TTS call (TTS only).", "type": "string" }, "voices": { "description": "For action=list: available voices with trimmed metadata (voice_id, name, accent, descriptive, age, language, use_case).", "type": "array" } }