{"uid":"cap_1UtoOucJqANy9e2SZqiw4","slug":"forgemesh-voice-long-form-text-to-speech-f40f9edc","name":"ForgeMesh Voice Long-Form Text-to-Speech","description":"OpenAI-compatible text-to-speech endpoint (input, voice, response_format) for drop-in use with existing OpenAI TTS clients, 1 of 10 standard voices, for 501-2000 characters, WAV/FLAC/OGG output. Use it to: voice a longer OpenAI-formatted request without an API key, migrate an existing TTS integration to pay-per-call pricing, synthesize extended text through a familiar request shape. USDC on Base via x402.","url":"https://voice.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_mjZzFtywvDadyhcQL7wWn","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 long-form text into spoken audio using persona voices across 31 languages, with pay-per-call x402 micropayment billing and an OpenAI-compatible API shape.","exampleAgentPrompt":"Read the following blog post out loud in English using a warm narrator voice and give me the audio as a WAV file: 'Welcome to ForgeMesh. Today we explore how AI agents can speak to the world in 31 languages with just a single API call.'","exampleUseCases":null,"resultDescription":"An audio file (WAV, FLAC, or OGG) containing the synthesized speech of the provided text, returned as an OpenAI-compatible audio response with the appropriate content-type header.","failureModes":["Payment not included or insufficient USDC — returns 402 Payment Required","Unsupported response_format value — returns 400 Bad Request","Text input missing or empty — returns 400 Bad Request","Requested voice name not found — may return 400 or fall back to default","Service temporarily unavailable — returns 503"],"whenToPreferThis":"Choose this endpoint when you need long-form text-to-speech synthesis with persona voices, multilingual support (31 languages), and an OpenAI-compatible request shape — especially in agentic workflows where pay-per-call x402 micropayments are preferred over subscription billing.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:33:46.704Z","isFirstParty":false}