{"uid":"cap_AYKBX8H_ha64pxshf3pMs","slug":"mapleai-audio-transcription-whisper-76511eeb","name":"MapleAI Audio Transcription (Whisper)","description":"14 chat models (GPT + Claude), 7 image models, and Jev structured decisions. Pay per request in USDC on Base with x402.","url":"https://base.mapleai.shop/v1/audio/transcriptions?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"file":{"type":"string","description":"Audio (mp3, wav, m4a, ogg, flac, webm) as base64 or data URI, max 25 MB; multipart/form-data with a file field works too"},"model":{"enum":["whisper-1","whisper-large-v3","whisper-large-v3-turbo"],"type":"string","default":"whisper-1"},"language":{"type":"string","description":"Optional ISO 639-1 hint"},"response_format":{"enum":["json","text","verbose_json","srt","vtt"],"type":"string","default":"json","description":"verbose_json (word timestamps) / srt / vtt require whisper-large-v3 or whisper-large-v3-turbo (groq backend)"}}},"responseSchema":{"type":"json","example":{"text":"Hello from MapleAI"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.007","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":"$0.007/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.007","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.007","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_gM0r9Yt5vXo9OVHzlN6IP","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.007","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes audio files to text using Whisper models, paid per request in USDC via x402 on Base.","exampleAgentPrompt":"Transcribe this meeting recording for me — it's a WAV file, use whisper-large-v3-turbo, and give me the output as an SRT subtitle file with timestamps.","exampleUseCases":[{"title":"Podcast transcript for show notes","prompt":"I have an MP3 of my podcast episode — can you transcribe it to plain text using whisper-1 so I can turn it into show notes?"},{"title":"Auto-captions for video content","prompt":"Generate VTT captions from this audio clip using whisper-large-v3-turbo so I can add subtitles to my video."},{"title":"Multilingual meeting transcription","prompt":"Transcribe this OGG recording of our French team meeting using whisper-large-v3 — set the language to 'fr' and give me verbose JSON with word-level timestamps."}],"resultDescription":"A JSON object containing a 'text' field with the full transcription. When using verbose_json format with large Whisper models, includes word-level timestamps. SRT and VTT formats return structured subtitle content suitable for video captioning.","failureModes":["Audio file exceeds 25 MB limit — request rejected","Unsupported audio format submitted — format error returned","verbose_json, srt, or vtt requested with whisper-1 — only large Whisper models support those formats via Groq backend","Payment of $0.0085 USDC not settled via x402 — 402 Payment Required response","Invalid base64 or malformed data URI — decoding error","Language hint is not a valid ISO 639-1 code — may fall back to auto-detection or error"],"whenToPreferThis":"Choose this endpoint when you need pay-per-request audio transcription without a subscription, billed in USDC on Base via x402. It is ideal for agents that process audio intermittently and need OpenAI Whisper-compatible output including SRT/VTT captions and word timestamps (via the large Whisper models on Groq). Prefer over OpenAI directly when you want crypto-native micropayment billing with no API key management.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T00:30:08.992Z","isFirstParty":false,"canonicalSlug":"mapleai-audio-transcription-whisper-76511eeb"}