{"uid":"cap_i-HdfRaPpTqXFLWfUEyHN","slug":"audio-withzero-xyz-openai-whisper-large-v3-audio-transcription-91c29fb2","name":"OpenAI Whisper Large v3 Audio Transcription","description":"Transcribe spoken audio to text with OpenAI Whisper Large v3.","url":"https://audio.withzero.xyz/api/v1/transcripts/whisper-large-v3","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","example":{"audio":"UklGRiYAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQIAAAAAAA==","format":"wav"},"required":["audio","format"],"properties":{"audio":{"type":"string","maxLength":20971524,"minLength":1,"description":"Base64-encoded audio to transcribe (decoded size up to 15 MB)."},"format":{"enum":["wav","mp3"],"type":"string","description":"Container format of the audio."}},"additionalProperties":false},"responseSchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["text","seconds","model","price_usdc"],"properties":{"text":{"type":"string","description":"The transcript of the audio."},"model":{"type":"string","description":"The model that produced the transcript."},"seconds":{"type":"number","description":"Detected duration of the input audio in seconds."},"price_usdc":{"type":"string","description":"The amount charged for this request, in USDC."}},"additionalProperties":false},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.002","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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":"$0.002/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_HOH_CJRf3NuQOyUjirtt5","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"audio.withzero.xyz","brandSlug":"audio-withzero-xyz-mpp","brandBaseUrl":"https://audio.withzero.xyz","brandDocsUrl":null,"whatItDoes":"Transcribes spoken audio (WAV or MP3, up to 15 MB base64-encoded) to text using OpenAI Whisper Large v3","exampleAgentPrompt":"Can you transcribe this MP3 audio file for me using Whisper Large v3? Here's the base64-encoded audio data: [base64string]","exampleUseCases":null,"resultDescription":"Returns a JSON object containing the full text transcript of the audio, the detected duration of the audio in seconds, the model name used (whisper-large-v3), and the USDC cost of the request.","failureModes":["Audio exceeds 15 MB decoded size — request rejected","Unsupported format provided (anything other than wav or mp3) — validation error","Malformed or invalid base64 encoding — decoding error","Audio contains no detectable speech — empty or near-empty transcript returned","Network timeout on large audio files — request fails with timeout error"],"whenToPreferThis":"Choose this endpoint when you need high-accuracy speech-to-text transcription using OpenAI's Whisper Large v3 model, especially for WAV or MP3 files up to 15 MB. Prefer this over the GPT-4o Transcribe endpoint when cost-efficiency or Whisper-specific behavior is required. Best suited for batch transcription of recorded audio, interviews, meetings, or podcasts.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-16T00:34:57.432Z","isFirstParty":true}