{"uid":"cap_L1MBQrF4lybNI4w7-9ohR","slug":"singit-speech-text-to-speech-via-multiple-voice-models-d44f4389","name":"SingIt Speech - Text-to-Speech via Multiple Voice Models","description":"SingIt Speech: Text read aloud by 11 voice models (Kokoro, ElevenLabs, Gemini, xAI, MiniMax and more; list at GET /v1/audio/models), no API key needed. Call it when an agent needs spoken audio made from text. OpenAI speech request format, mp3 by default.","url":"https://ask.singitai.app/v1/audio/speech?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"input":{"type":"string","maxLength":4096,"minLength":1,"description":"The text to read aloud."},"model":{"type":"string","examples":["venice-kokoro-tts"],"description":"A speech model id from GET /v1/audio/models."},"speed":{"type":"number","maximum":4,"minimum":0.25,"description":"Speaking speed."},"voice":{"type":"string","examples":["af_heart"],"maxLength":60,"description":"A voice of the model; they are listed at GET /v1/audio/models."},"response_format":{"enum":["mp3","opus","aac","flac","wav","pcm"],"type":"string","default":"mp3","description":"The audio format."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001082","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":"$1.301/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"1.301","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"1.301","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Nrsscx24GAY-PAPuJ9OE2","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"1.301","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts text to spoken audio using one of 11+ voice models (Kokoro, ElevenLabs, Gemini, xAI, MiniMax, etc.), billed per request via x402 micropayments in USDC","exampleAgentPrompt":"Read this aloud using ElevenLabs: 'Welcome to our store. Today's specials are 20% off all electronics.' — give me back an MP3.","exampleUseCases":[{"title":"Narrating a blog post for podcast","prompt":"Take the intro paragraph of my article — 'Artificial intelligence is reshaping how we work and create' — and read it aloud in a natural voice using Gemini. I want an MP3 I can embed in my site."},{"title":"Voiceover for app onboarding","prompt":"I need audio for my app's welcome screen. Please use MiniMax to say: 'Hi there, welcome to FlowTrack. Let's get you set up in just a few steps.' Return it as an MP3."},{"title":"Accessible reading for long document","prompt":"Read this passage aloud with Kokoro: 'The quarterly report shows a 12% increase in revenue driven primarily by subscription growth.' I need it as an audio file for our accessibility feature."}],"resultDescription":"Returns an MP3 audio file (or other requested format) of the input text spoken by the chosen voice model. No audio is generated or charged if there is a processing failure. The response follows OpenAI's speech endpoint format.","failureModes":["Invalid or unsupported voice model name returns an error","Insufficient USDC balance causes payment failure and no audio is returned","Empty or missing input text returns a validation error","Unsupported audio format request may default to MP3 or return an error","Network or provider-side failure from the underlying TTS provider (ElevenLabs, Gemini, etc.)"],"whenToPreferThis":"Choose this endpoint when you need text-to-speech without managing API keys or subscriptions across multiple TTS providers. Ideal for agents that need pay-per-use voice synthesis billed via x402 micropayments in USDC, access to a broad selection of voice models in one OpenAI-compatible interface, and no upfront account setup.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T00:30:41.374Z","isFirstParty":false,"canonicalSlug":"singit-speech-text-to-speech-via-multiple-voice-models-d44f4389"}