{"uid":"cap_A9kmcpmENGqycOPdOMQf-","slug":"audio-withzero-xyz-gpt-4o-audio-transcription-0ee947c3","name":"GPT-4o Audio Transcription","description":"Transcribe spoken audio to text with OpenAI's GPT-4o Transcribe.","url":"https://audio.withzero.xyz/api/v1/transcripts/gpt-4o-transcribe?utm_source=zero.xyz","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":"0.005","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","requiresHandshake":false,"reviewCount":1,"rating":{"score":"0.08","successRate":"0.07","reviews":1,"stars":"1.3","state":"rated"},"availabilityStatus":"down","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.005/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_bD9-F01XH6vmR1X6HDHpI","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.005","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 base64-encoded spoken audio (WAV or MP3) to text using OpenAI's GPT-4o Transcribe model","exampleAgentPrompt":"Can you transcribe this MP3 audio file for me? I'll send it as base64 — use GPT-4o Transcribe to turn the speech into text.","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 (GPT-4o Transcribe), and the USDC price charged for the request.","failureModes":["Audio exceeds 15 MB decoded size — returns validation error","Unsupported audio format provided (not wav or mp3) — returns enum validation error","Malformed or invalid base64 encoding — returns decoding error","Audio contains no detectable speech — may return empty transcript","Network timeout for long audio files"],"whenToPreferThis":"Choose this endpoint when you need high-accuracy speech-to-text transcription using OpenAI's latest GPT-4o Transcribe model, especially for WAV or MP3 audio up to 15 MB. Prefer this over Whisper-based endpoints when you want GPT-4o's superior language understanding and transcription quality. Ideal for agents working with voice memos, meeting recordings, or spoken commands.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":16,"lastUsedAt":"2026-07-29T00:21:19.938Z","lastSuccessfullyRanAt":"2026-06-16T13:15:59.665Z","lastHealthCheckAt":"2026-10-12T18:34:31.669Z","isFirstParty":true,"canonicalSlug":"audio-withzero-xyz-gpt-4o-audio-transcription-0ee947c3"}