{"uid":"cap_5D4x48IkdaZjvrlyPIhjD","slug":"x402factory-ai-speech-to-text-base-usdc-938f2d50","name":"x402Factory.ai Speech-to-Text (Base/USDC)","description":"Base speech-to-text endpoint using x402 payments. Provide either a YouTube URL/ID or a direct audio file URL; the server downloads the audio, runs speech-to-text, and returns the transcript text. Pricing: 0.01 USDC per started minute of audio, computed from the estimated duration and charged upfront via x402. Default discovery price without a specific URL is 0.60 USDC as an upper-bound quote. When called without a specific URL, the endpoint returns a default discovery quote. Clients should re-run discovery with a concrete URL to get an exact quote based on the real audio duration.","url":"https://x402factory.ai/base/stt","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"youtube":{"type":"string","description":"YouTube video URL (e.g. https://www.youtube.com/watch?v=...) or 11-character video ID. For paid calls, either youtube or file_url is required."},"file_url":{"type":"string","description":"Direct URL to an audio file (e.g. .mp3, .webm). Must be an http(s) URL. For paid calls, either youtube or file_url is required."}}},"responseSchema":{"ok":{"type":"boolean","description":"True on success."},"text":{"type":"string","description":"Full transcript text returned by the speech-to-text engine (top-level 'text' field)."},"action":{"type":"string","description":"Action performed. For this endpoint: 'stt'."},"source":{"type":"string","description":"Source type used for transcription: 'youtube' or 'file_url'."},"file_url":{"type":"string","description":"Direct file URL that was processed when source = 'file_url'."},"video_id":{"type":"string","description":"YouTube video ID that was processed."},"price_usdc":{"type":"number","description":"Price charged for this call in USDC (6 decimals). Computed as 0.01 USDC per started minute of audio."},"youtube_url":{"type":"string","description":"Resolved YouTube URL that was processed."},"duration_minutes":{"type":"number","description":"Duration rounded up to whole minutes, used for pricing (0.01 USDC per minute)."},"duration_seconds":{"type":"number","description":"Audio duration in seconds when available (YouTube metadata or estimated from file size)."}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.6","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":"$0.6/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.6","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.6","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_DeRfi7fPYRDEOYPKszJLp","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.6","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes audio from a YouTube video or direct audio file URL into text, charging 0.01 USDC per minute via x402 micropayment on Base.","exampleAgentPrompt":"Can you transcribe this YouTube video for me? Here's the URL: https://www.youtube.com/watch?v=dQw4w9WgXcQ — I need the full spoken transcript.","exampleUseCases":null,"resultDescription":"Returns a JSON object with ok=true on success, the full transcript as a plain text string in the 'text' field, the source type used ('youtube' or 'file_url'), the resolved URL or video ID processed, the audio duration in seconds and rounded-up minutes, and the exact USDC price charged for the call.","failureModes":["Invalid or inaccessible YouTube URL/ID returns an error with ok=false","Audio file URL is unreachable or not a supported format","Payment insufficient for the actual audio duration — discovery quote may underestimate for long content","Called without a URL returns a discovery quote (0.60 USDC upper bound) rather than a real transcript","Network timeout downloading large audio files"],"whenToPreferThis":"Use this endpoint when you need to transcribe audio from a YouTube video or a direct audio file URL and want per-minute micropayment pricing (0.01 USDC/minute) via x402 on Base rather than a traditional API key subscription. Ideal for pay-as-you-go transcription of varying-length content without upfront commitment.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T17:54:08.049Z","isFirstParty":false}