{"uid":"cap_QmN0ZThdJ5MUyg6zd3yIc","slug":"mapleai-text-to-speech-api-x402-pay-per-request-ceba764f","name":"MapleAI Text-to-Speech API (x402 Pay-Per-Request)","description":"14 chat models (GPT + Claude), 7 image models, and Jev structured decisions. Pay per request in USDC on Base with x402.","url":"https://base.mapleai.shop/v1/audio/speech?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"input":{"type":"string","description":"Text to synthesize, 1-5000 characters"},"model":{"enum":["tts-1","tts-1-hd","orpheus-english","orpheus-arabic"],"type":"string","description":"tts-1 = fast Gemini Flash-Lite, tts-1-hd = fuller Gemini Flash, orpheus-english/orpheus-arabic = emotive Groq Orpheus (en voices autumn/diana/hannah/austin/daniel/troy, ar voices fahad/sultan/noura/lulwa/aisha/abdullah; emotion tags like [laughs] supported)"},"speed":{"type":"number","maximum":4,"minimum":0.25},"voice":{"type":"string","description":"Voice preset (alloy, echo, fable, onyx, nova, shimmer…) or a Gemini voice name; default alloy"},"response_format":{"enum":["wav"],"type":"string","default":"wav"}}},"responseSchema":{"type":"json","example":{"audio":"binary WAV stream (audio/wav)","format":"RIFF/WAVE 24 kHz mono"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.016","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.016/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.016","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.016","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_hA_qSN3zhbQnHwzXnjFeZ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.016","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Synthesizes spoken audio from text using multiple TTS models including Gemini Flash and Groq Orpheus, returning a WAV audio stream, paid per request in USDC via x402.","exampleAgentPrompt":"Can you read this out loud using the Orpheus English model with the 'autumn' voice — here's the text: 'Welcome to our quarterly review. Things are going really well this year [laughs].'","exampleUseCases":[{"title":"Emotive podcast intro narration","prompt":"Turn this intro script into speech using the orpheus-english model with the 'diana' voice, and include a [laughs] tag after the joke — text is: 'Welcome back, folks. Today we cover the wildest AI stories of the week [laughs]. Buckle up.'"},{"title":"Arabic voice announcement generation","prompt":"Synthesize this Arabic announcement using the orpheus-arabic model with the 'noura' voice: 'مرحباً بكم في المنصة الجديدة. نأمل أن تستمتعوا بتجربتكم.'"},{"title":"High-quality audiobook segment","prompt":"Convert this paragraph to high-quality speech using the tts-1-hd model with the 'fable' voice at 0.9 speed: 'The old lighthouse stood at the edge of the world, its beam cutting through the fog like a whisper of hope.'"}],"resultDescription":"A binary WAV audio stream in RIFF/WAVE format at 24 kHz mono, returned as audio/wav content. The audio contains the synthesized speech of the provided input text using the selected model and voice.","failureModes":["Input text exceeds 5000 characters — request rejected","Invalid model name supplied — enum validation error","Invalid voice name for selected model — may fall back to default or error","Payment not settled via x402 — 402 Payment Required response","Speed value outside 0.25–4.0 range — validation error","Groq Orpheus model unavailable — upstream service error"],"whenToPreferThis":"Choose this endpoint when you need pay-per-use TTS without a subscription, especially when you want emotive speech with emotion tags (e.g. [laughs]) via Groq Orpheus, or Arabic-language voice synthesis. Ideal for agents that generate audio on demand and pay per call in USDC on Base. Prefer over OpenAI TTS directly if you want crypto-native billing or access to Orpheus voices not available on OpenAI.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T00:41:31.927Z","isFirstParty":false,"canonicalSlug":"mapleai-text-to-speech-api-x402-pay-per-request-ceba764f"}