{"uid":"cap_US78F4cVNhfR3EJlHkzTf","slug":"forgemesh-voice-batch-long-form-tts-81c27f4c","name":"ForgeMesh Voice Batch Long-Form TTS","description":"Batch text-to-speech: synthesize up to 20 text items in a single call, standard voices only, for 501-2000 total characters, returns JSON with base64 WAV audio plus duration and sample rate per item. Use it to: batch-voice a longer set of messages, produce audio for a multi-section script or FAQ, generate several paragraph-length voice clips in one request without repeated calls. USDC on Base via x402.","url":"https://voice.forgemesh.io/v1/tts/batch-long","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"items":{"type":"array","items":{"type":"object","required":["text"],"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 for this batch item"},"voice":{"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"],"type":"string","description":"Standard voice: M1-M5 or F1-F5"}},"additionalProperties":false},"maxItems":20,"minItems":1,"description":"Array of standard-voice text items. Total text across all items must be <= 2000 characters; use /v1/tts/batch for <=500 total chars and /v1/tts/batch-long for 501-2000 total chars."},"defaults":{"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"},"voice":{"enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5"],"type":"string","description":"Standard voice: M1-M5 or F1-F5"}},"description":"Default standard voice and language for all items","additionalProperties":false}}},"responseSchema":{"type":"json","example":{"items":[{"format":"wav","duration_s":1.5,"sample_rate":44100,"audio_base64":"..."}]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_v4eLA8uCXcUn6I4j_ldLt","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts a batch of up to 20 text items into spoken audio using persona voices across 31 languages, returning base64-encoded WAV audio for each item.","exampleAgentPrompt":"Convert these 5 chapter summaries to speech using a warm male narrator voice in English and send back the audio: [chapter text 1], [chapter text 2], [chapter text 3], [chapter text 4], [chapter text 5].","exampleUseCases":null,"resultDescription":"A JSON object containing an array of items, each with a base64-encoded WAV audio string, the audio duration in seconds, and the audio format label — one result per input text item.","failureModes":["More than 20 items submitted — batch limit exceeded","Unsupported language code — returns error for unrecognized lang value","Invalid or non-base voice specified — persona voices not accepted in batch-long endpoint","Payment failure via x402 — call not processed if USDC payment is rejected","Empty text items — may return zero-duration audio or validation error","Malformed items array — missing required text field causes schema validation failure"],"whenToPreferThis":"Choose this endpoint when you need to synthesize multiple distinct text passages in a single API call (up to 20 items), especially for long-form content like book chapters, video scripts, or batched agent responses. Prefer this over single-item TTS endpoints when throughput efficiency matters and you want to minimize per-request overhead across many texts. Best suited for batch pipeline workflows where audio is consumed asynchronously.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:35:03.919Z","isFirstParty":false}