{"uid":"cap_RmccUYKNJFCvUXzX1cT8t","slug":"forgemesh-text-to-speech-long-form-48b0db5c","name":"ForgeMesh Text-to-Speech (Long-Form)","description":"Paid text-to-speech via x402. WAV audio in 31 languages, OpenAI-compatible, no API keys.","url":"https://tts.forgemesh.io/v1/audio/speech-long","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"input":{"type":"string","maxLength":2000,"minLength":1,"description":"OpenAI-compatible text input to synthesize, max 2000 characters"},"model":{"type":"string","description":"Ignored — always uses ForgeMesh Voice"},"voice":{"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"],"type":"string","description":"Standard voice: M1-M5 or F1-F5"},"response_format":{"enum":["wav","flac","ogg"],"type":"string","description":"Requested audio format"}}},"responseSchema":{"type":"json","example":{"description":"OpenAI-compatible inline speech audio response","content_type":"audio/wav"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_6FWyYsJRuJ-Okcj5m1-Dx","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts up to 2000 characters of text into spoken audio (WAV/FLAC/OGG) across 31 languages using a selection of male and female voices, paid per-call via x402 micropayments with no API key required.","exampleAgentPrompt":"Read this script aloud using a female voice (F2) and give me a WAV file: 'Welcome to ForgeMesh. Your AI-powered audio experience starts here. This message is available in 31 languages.'","exampleUseCases":[{"title":"Multilingual product announcement narration","prompt":"I need to turn this product announcement into spoken audio using a professional male voice — use M3 and give me a WAV file: 'Introducing our new wireless headphones. Crystal-clear sound, 40-hour battery life, and a sleek foldable design.'"},{"title":"Accessible reading for web article","prompt":"Convert this article excerpt into audio so visually impaired users can listen to it — use the F1 voice and return it as an OGG file: 'Climate scientists have confirmed that 2024 was the hottest year on record, surpassing the previous record set just a year earlier.'"},{"title":"Voiceover for app onboarding flow","prompt":"Generate a friendly spoken greeting for my app's onboarding screen using the M2 voice in WAV format: 'Hi there! Let's get you set up. It only takes two minutes to create your account and start exploring.'"}],"resultDescription":"Returns an audio file (WAV by default, or FLAC/OGG if specified) containing the synthesized speech for the provided text, using the selected voice. The response is an OpenAI-compatible inline audio payload with the appropriate content-type header (audio/wav, audio/flac, or audio/ogg).","failureModes":["Payment failure: x402 micropayment not processed or insufficient USDC balance — request rejected before synthesis","Input too long: text exceeds 2000 characters — validation error returned","Invalid voice ID: value outside M1-M5/F1-F5 enum — bad request error","Unsupported format: response_format not in wav/flac/ogg — ignored or error","Service unavailability: ForgeMesh Voice backend timeout or downtime — 5xx error"],"whenToPreferThis":"Choose this endpoint when you need OpenAI-compatible TTS without managing API keys, want to pay per call via x402 USDC micropayments, need multilingual support across 31 languages, or want a choice of 10 distinct voices (5 male, 5 female). It is especially well-suited for agents that already handle x402 payment flows and need audio generation as a drop-in capability without account provisioning.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T17:51:15.200Z","isFirstParty":false}