{"version":"2","voice_tier_rules":{"base_voices":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"],"standard_voices":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"],"persona_voices":["Storyteller","Narrator","Announcer","Assistant","Urgent","Sage","Spark","Anchor","Velvet","Echo"],"persona_endpoint":"/v1/tts/custom","openai_endpoint_standard_voices_only":true},"expressive_controls":{"speed":{"tier":"pro_or_custom","parameter":"speed","range":[0.7,2],"default":1.05,"presets":{"slow":0.7,"normal":1,"fast":1.3,"rapid":1.6}},"quality":{"tier":"pro_or_custom","parameter":"steps","range":[1,100],"default":8,"presets":{"draft":4,"standard":8,"high":16,"ultra":24}},"persona_voices":{"tier":"custom","endpoint":"/v1/tts/custom","note":"Persona voices are prebuilt expressive blends. Use the persona voice name in the voice field.","recipes":{"Storyteller":"warm measured narration, M1+F3 blend, slower pace","Narrator":"neutral documentary narration, M3+F3 blend","Announcer":"crisp authoritative announcement voice, M2+M5 blend","Assistant":"friendly clear assistant voice, F1+F4 blend","Urgent":"sharp alert voice, M4+F2 blend, faster pace","Sage":"deep calm wellness voice","Spark":"energetic youthful voice","Anchor":"authoritative report voice","Velvet":"warm rich premium voice","Echo":"androgynous neutral accessibility voice"}},"route_rules":{"base":"10 base voices only (M1-M5, F1-F5); no speed, steps, or personas","pro":"10 base voices only (M1-M5, F1-F5) with speed and steps; no personas","custom":"all 20 voices: base voices plus Custom-only persona voices with speed and steps","openai":"OpenAI-shaped request for the 10 base voices only; no personas","batch":"10 base voices only (M1-M5, F1-F5); no speed, steps, or personas"}},"endpoints":[{"method":"POST","path":"/v1/tts/base","price":"$0.001","description":"Generate standard voice — low-cost WAV speech with 10 standard voices, 31 languages, and up to 500 chars for $0.001","params":{"text":{"type":"string","required":true,"maxLength":500},"voice":{"type":"string","required":false,"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"]},"lang":{"type":"string","required":false,"enum":["en","ko","ja","ar","bg","cs","da","de","el","es","et","fi","fr","hi","hr","hu","id","it","lt","lv","nl","pl","pt","ro","ru","sk","sl","sv","tr","uk","vi"]},"speed":{"type":"number","required":false},"steps":{"type":"integer","required":false}}},{"method":"POST","path":"/v1/tts/base-long","price":"$0.003","description":"Generate standard voice long — low-cost WAV speech with 10 standard voices, 31 languages, and 501-2000 chars for $0.003","params":{"text":{"type":"string","required":true,"maxLength":2000},"voice":{"type":"string","required":false,"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"]},"lang":{"type":"string","required":false,"enum":["en","ko","ja","ar","bg","cs","da","de","el","es","et","fi","fr","hi","hr","hu","id","it","lt","lv","nl","pl","pt","ro","ru","sk","sl","sv","tr","uk","vi"]},"speed":{"type":"number","required":false},"steps":{"type":"integer","required":false}}},{"method":"POST","path":"/v1/tts/pro","price":"$0.003","description":"Generate controlled voice — WAV speech with granular speed and quality controls, 10 standard voices, and up to 500 chars for $0.003","params":{"text":{"type":"string","required":true,"maxLength":500},"voice":{"type":"string","required":false,"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"]},"lang":{"type":"string","required":false,"enum":["en","ko","ja","ar","bg","cs","da","de","el","es","et","fi","fr","hi","hr","hu","id","it","lt","lv","nl","pl","pt","ro","ru","sk","sl","sv","tr","uk","vi"]},"speed":{"type":"number","required":false},"steps":{"type":"integer","required":false}}},{"method":"POST","path":"/v1/tts/pro-long","price":"$0.006","description":"Generate controlled voice long — WAV speech with granular speed and quality controls, 10 standard voices, and 501-2000 chars for $0.006","params":{"text":{"type":"string","required":true,"maxLength":2000},"voice":{"type":"string","required":false,"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"]},"lang":{"type":"string","required":false,"enum":["en","ko","ja","ar","bg","cs","da","de","el","es","et","fi","fr","hi","hr","hu","id","it","lt","lv","nl","pl","pt","ro","ru","sk","sl","sv","tr","uk","vi"]},"speed":{"type":"number","required":false},"steps":{"type":"integer","required":false}}},{"method":"POST","path":"/v1/tts/custom","price":"$0.005","description":"Generate persona voice — expressive WAV speech with 20 voices including Assistant, Storyteller, Velvet, Urgent, and up to 500 chars for $0.005","params":{"text":{"type":"string","required":true,"maxLength":500},"voice":{"type":"string","required":false,"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5","Storyteller","Narrator","Announcer","Assistant","Urgent","Sage","Spark","Anchor","Velvet","Echo"]},"lang":{"type":"string","required":false,"enum":["en","ko","ja","ar","bg","cs","da","de","el","es","et","fi","fr","hi","hr","hu","id","it","lt","lv","nl","pl","pt","ro","ru","sk","sl","sv","tr","uk","vi"]},"speed":{"type":"number","required":false},"steps":{"type":"integer","required":false}}},{"method":"POST","path":"/v1/tts/custom-long","price":"$0.01","description":"Generate persona voice long — expressive WAV speech with 20 voices, speed/quality controls, and 501-2000 chars for $0.01","params":{"text":{"type":"string","required":true,"maxLength":2000},"voice":{"type":"string","required":false,"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5","Storyteller","Narrator","Announcer","Assistant","Urgent","Sage","Spark","Anchor","Velvet","Echo"]},"lang":{"type":"string","required":false,"enum":["en","ko","ja","ar","bg","cs","da","de","el","es","et","fi","fr","hi","hr","hu","id","it","lt","lv","nl","pl","pt","ro","ru","sk","sl","sv","tr","uk","vi"]},"speed":{"type":"number","required":false},"steps":{"type":"integer","required":false}}},{"method":"POST","path":"/v1/audio/speech","price":"$0.001","description":"Generate OpenAI-compatible voice — OpenAI-shaped speech request with input, voice, model, and response_format fields for $0.001","params":{"input":{"type":"string","required":true,"maxLength":500},"voice":{"type":"string","required":false,"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"]},"model":{"type":"string","required":false},"response_format":{"type":"string","required":false,"enum":["wav","flac","ogg"]}}},{"method":"POST","path":"/v1/audio/speech-long","price":"$0.003","description":"Generate OpenAI-compatible voice long — OpenAI-shaped speech request for 501-2000 chars, 10 standard voices, and x402 payment for $0.003","params":{"input":{"type":"string","required":true,"maxLength":2000},"voice":{"type":"string","required":false,"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"]},"model":{"type":"string","required":false},"response_format":{"type":"string","required":false,"enum":["wav","flac","ogg"]}}},{"method":"POST","path":"/v1/tts/batch","price":"$0.002","description":"Generate batch voices — WAV audio for up to 20 standard-voice texts in one paid call for $0.002","params":{"items":{"type":"array","required":true,"maxItems":20,"description":"Array of {text, voice?, lang?} items; base voices only"},"defaults":{"type":"object","required":false,"description":"Default base voice and lang for all items"}}},{"method":"POST","path":"/v1/tts/batch-long","price":"$0.005","description":"Generate batch voices long — WAV audio for up to 20 standard-voice texts and 501-2000 total chars for $0.005","params":{"items":{"type":"array","required":true,"maxItems":20,"description":"Array of {text, voice?, lang?} items; base voices only"},"defaults":{"type":"object","required":false,"description":"Default base voice and lang for all items"}}}]}