{"uid":"cap_ATNWrZQ5cr3G80R_P1eld","slug":"microsoft-ai-audio-transcriptions-via-openrouter-6289c0dd","name":"Microsoft AI Audio Transcriptions via OpenRouter","description":"Transcribe base64 PCM WAV (mono, 16-bit, 16 kHz, up to 10 minutes; models and prices at GET /v1/audio/models)","url":"https://microsoft-ai.mpp.tempo.xyz/v1/audio/transcriptions?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":null,"responseSchema":null,"example":null,"exampleRequest":null,"tags":["ai"],"displayCostAmount":"unknown","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"unknown_unparsed","priceSource":"registry","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":"unknown","summary":"price unknown","primary":{"kind":"unknown","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"},"accepted":[{"kind":"unknown","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"}]},"paymentMethods":[{"uid":"pm_kAj2Wg-fpJwmxi1PLgyLE","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"unknown","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"Microsoft AI","brandSlug":"microsoft-ai-mpp","brandBaseUrl":"https://openrouter.ai","brandDocsUrl":"https://openrouter.ai","whatItDoes":"Transcribes base64-encoded PCM WAV audio (mono, 16-bit, 16 kHz, up to 10 minutes) into text using Microsoft AI speech models","exampleAgentPrompt":"Can you transcribe this audio recording for me? I have a mono 16-bit 16 kHz WAV file encoded in base64 — it's about 3 minutes long and I need the spoken content converted to text using Microsoft's speech model.","exampleUseCases":[{"title":"Meeting notes from recorded call","prompt":"I recorded our team standup as a WAV file and encoded it to base64 — can you transcribe the audio so I have written notes from the meeting? It's about 8 minutes, mono, 16 kHz."},{"title":"Voice memo to written draft","prompt":"I have a base64-encoded voice memo I recorded on my phone — it's a mono 16-bit 16 kHz WAV. Please transcribe what I said so I can turn it into a written draft."},{"title":"Customer support call transcript","prompt":"Transcribe this base64 PCM WAV recording of a customer support call — it's under 10 minutes, mono, 16 kHz — so I can review what was said and log it in our system."}],"resultDescription":"A text transcript of the spoken content from the provided audio, extracted from the base64-encoded PCM WAV input using the selected Microsoft AI speech model.","failureModes":["Audio exceeds 10-minute duration limit — request rejected","Invalid base64 encoding causes decoding failure","Audio format mismatch (not mono, not 16-bit, or not 16 kHz) leads to poor results or error","Unsupported model identifier specified","Payment failure or insufficient USDC balance prevents call","Network timeout on large audio payloads"],"whenToPreferThis":"Choose this endpoint when you need to transcribe short-to-medium duration audio (up to 10 minutes) in mono PCM WAV format via Microsoft AI's speech models, especially when operating in a crypto-native or agent payment context using USDC on-chain micropayments via the MPP/x402 protocol. Prefer this over generic STT APIs when you need Microsoft's specific model quality or when integrating into a Coinbase-curated agent ecosystem.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-29T13:08:05.664Z","isFirstParty":false,"canonicalSlug":"microsoft-ai-audio-transcriptions-via-openrouter-6289c0dd"}