{"slug":"voice-forgemesh-io-v1-tts-custom-long-443f8e","title":"Expressive text-to-speech in any of 20 voices, standard M1-M5/F1-F5 plus persona","host":"voice.forgemesh.io","method":"POST","resource":"https://voice.forgemesh.io/v1/tts/custom-long","category":"image","description":"Expressive text-to-speech in any of 20 voices, standard M1-M5/F1-F5 plus personas like Storyteller, Narrator, Announcer, Urgent, Velvet, with speed and quality control, for 501-2000 characters, WAV output. Use it to: narrate a longer story or audiobook chapter, voice an extended character monologue,","price_listed":0.01,"price_asked":0.01,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":243,"reported_calls_30d":4,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"lang":"en","text":"Hello world","voice":"M1"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"lang":{"description":"Language code; 31 languages supported","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"},"speed":{"description":"Pro/Custom expressive speed control, 0.7-2.0. Presets: slow 0.7, normal 1.0, fast 1.3, rapid 1.6","maximum":2,"minimum":0.7,"type":"number"},"steps":{"description":"Pro/Custom quality control, 1-100. Presets: draft 4, standard 8, high 16, ultra 24","maximum":100,"minimum":1,"type":"integer"},"text":{"description":"Text to synthesize into speech, max 2000 characters. Use non-long routes for 1-500 chars and -long routes for 501-2000 chars.","maxLength":2000,"minLength":1,"type":"string"},"voice":{"description":"Voice name. Standard voices M1-M5/F1-F5; persona voices require Custom tier.","enum":["M1","M2","M3","M4","M5","F1","F2","F3","F4","F5","Storyteller","Narrator","Announcer","Assistant","Urgent","Sage","Spark","Anchor","Velvet","Echo"],"type":"string"}},"required":["text"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"audio":{"description":"Inline WAV bytes in the HTTP response body","type":"string"},"content_type":{"const":"audio/wav","type":"string"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":243,"error":null}],"description_full":"Expressive text-to-speech in any of 20 voices, standard M1-M5/F1-F5 plus personas like Storyteller, Narrator, Announcer, Urgent, Velvet, with speed and quality control, for 501-2000 characters, WAV output. Use it to: narrate a longer story or audiobook chapter, voice an extended character monologue, produce a branded multi-sentence announcement, script a persona-driven podcast segment. USDC on Base via x402.","last_updated":"2026-09-21T08:37:36.477Z","schemes":["exact"]}