{"uid":"cap_Zr0dXfiXxdRMY8oX5MOtu","slug":"forgemesh-voice-text-to-speech-api-af145fa5","name":"ForgeMesh Voice Text-to-Speech API","description":"OpenAI-compatible text-to-speech endpoint (input, voice, response_format) for drop-in use with code already built against the OpenAI TTS API, 1 of 10 standard voices, up to 500 characters, WAV/FLAC/OGG output. Use it to: swap OpenAI TTS calls for a pay-per-call x402 alternative, generate speech from an existing OpenAI-style client, avoid API-key management for short text-to-audio requests. USDC on Base.","url":"https://voice.forgemesh.io/v1/audio/speech","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":"0.001","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_10qCEfmdX98c2eVd4MgOe","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","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 in multiple languages using persona voices, returning an audio file in OpenAI-compatible format via pay-per-call x402 micropayments.","exampleAgentPrompt":"Read this paragraph aloud using a calm female persona voice and give me the audio as a WAV file: 'Welcome to ForgeMesh, where your AI agent finally has a voice worth hearing.'","exampleUseCases":null,"resultDescription":"An audio file (WAV, FLAC, or OGG) containing the synthesized speech of the input text, returned as a binary audio response with the appropriate content-type header (e.g. audio/wav). The response is OpenAI-compatible.","failureModes":["Payment not included or invalid x402 USDC payment — returns 402 Payment Required","Unsupported response_format value (not wav, flac, or ogg) — returns 400 Bad Request","Empty or missing input text — returns 400 Bad Request","Unsupported or unknown voice name — returns 400 or falls back to default voice","Service unavailable or overloaded — returns 503"],"whenToPreferThis":"Choose this endpoint when you need a pay-per-call, no-subscription TTS API that is OpenAI speech API-compatible, supports persona voices, covers 31 languages, and accepts x402 USDC micropayments — ideal for AI agents, serverless apps, or any workflow where you want to pay only per synthesis call without managing API keys or subscriptions.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:39:54.470Z","isFirstParty":false}