{"uid":"cap_2TdyzH44xdmMhvHkL1M0m","slug":"forgemesh-voice-tts-base-long-94892fb6","name":"ForgeMesh Voice TTS Base Long","description":"Text-to-speech synthesis in 1 of 10 standard voices (M1-M5 male, F1-F5 female) across 31 languages, for longer text from 501 up to 2000 characters, returned as inline WAV audio. Use it to: read a full paragraph aloud, narrate a multi-sentence agent summary, voice an email or article excerpt, turn a longer LLM response into spoken audio, generate audio for a script section. USDC on Base via x402, no API key.","url":"https://voice.forgemesh.io/v1/tts/base-long","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"lang":{"enum":["en","ko","ja","ar","bg","cs","da","de","el","es","et","fi","fr","hi","hr","hu","id","it","lt","lv","nl","pl","pt","ro","ru","sk","sl","sv","tr","uk","vi"],"type":"string","description":"Language code; 31 languages supported"},"text":{"type":"string","maxLength":2000,"minLength":1,"description":"Text to synthesize into speech, max 2000 characters. Use non-long routes for 1-500 chars and -long routes for 501-2000 chars."},"voice":{"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"],"type":"string","description":"Standard voice: M1-M5 or F1-F5"}}},"responseSchema":{"type":"json","example":{"description":"44.1kHz 16-bit mono WAV speech audio returned inline","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_t8q1KP17jSIG5mJe1PjbZ","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 (up to 2000 chars) to speech in 44.1kHz WAV audio using configurable persona voices across 31 languages, billed per-call via x402 USDC micropayments.","exampleAgentPrompt":"Read this 500-word travel essay aloud using the Storyteller persona voice in English at normal speed, and give me a WAV file I can drop into my video: 'The ancient streets of Lisbon wind uphill through neighborhoods that smell of salt and sardines...'","exampleUseCases":[{"title":"Multilingual customer support message delivery","prompt":"Our chatbot just resolved a support ticket for a German customer. Take the confirmation message and convert it to natural-sounding German speech using the Narrator persona so we can send them an audio notification instead of text."},{"title":"Podcast episode intro narration generation","prompt":"I have a 1500-character intro script for tomorrow's podcast episode. Turn it into audio using the Storyteller voice in English at high quality—I need it to sound warm and engaging, like a real host reading it live."},{"title":"Children's audiobook chapter production","prompt":"I'm creating an audiobook for my illustrated French children's story. Generate the speech audio for chapter two using a friendly persona voice in French, and make sure it's clear and slow enough for young readers to follow along."}],"resultDescription":"A 44.1kHz 16-bit mono WAV audio file containing synthesized speech of the provided text, returned with content_type audio/wav. Quality and delivery depend on selected diffusion steps and speed parameters.","failureModes":["Text exceeds 2000 character limit — request rejected or truncated","Unsupported language code provided — synthesis fails or falls back","Invalid voice identifier (outside M1-M5, F1-F5, or recognized persona names) — error returned","Speed or steps parameter out of range — validation error","x402 payment failure or insufficient USDC balance — 402 response, no audio returned","Network timeout on longer texts with high diffusion steps"],"whenToPreferThis":"Choose this endpoint when you need long-form TTS (up to 2000 chars) with fine-grained control over voice personas, diffusion quality steps, and multilingual support, especially in agentic or automated pipelines that benefit from x402 micropayment billing with no subscription overhead. Prefer over generic TTS APIs when persona-style voices (Storyteller, Narrator) or per-call crypto payments are required.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:43:33.720Z","isFirstParty":false}