{"uid":"cap_9n-Xz_Cr9XUiI60o8D4Sj","slug":"openrouter-audio-transcriptions-16fad4d9","name":"OpenRouter Audio Transcriptions","description":"Transcribe base64 PCM WAV (mono, 16-bit, 16 kHz, up to 10 minutes; models and prices at GET /v1/audio/models)","url":"https://openrouter.mpp.tempo.xyz/v1/audio/transcriptions?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":null,"responseSchema":null,"example":null,"exampleRequest":null,"tags":["llm","unified","multi-model","chat","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_rpXfyq2tdxwjBx7s-ffnV","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"unknown","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"OpenRouter","brandSlug":"openrouter","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 multiple AI models","exampleAgentPrompt":"Can you transcribe this WAV audio recording I have — it's a mono 16-bit 16kHz file, about 3 minutes long — and give me the full text of what was said?","exampleUseCases":[{"title":"Meeting notes from voice recording","prompt":"I recorded our team standup meeting as a WAV file — mono, 16kHz — can you transcribe it so I have written notes to share with the team?"},{"title":"Podcast episode transcription","prompt":"I have a 9-minute podcast segment saved as a base64 PCM WAV at 16kHz mono — can you transcribe it into text so I can post a written version on the website?"},{"title":"Voice memo to text","prompt":"I left myself a voice memo as a WAV recording and need it converted to text — it's a mono 16-bit 16kHz file, about 90 seconds long. Can you transcribe it for me?"}],"resultDescription":"A text transcript of the spoken content from the submitted audio, extracted by an AI speech recognition model. The response contains the recognized words and sentences from the audio recording.","failureModes":["Audio not in expected format (must be base64 PCM WAV, mono, 16-bit, 16 kHz) — returns format error","Audio exceeds 10-minute limit — rejected with duration error","Invalid or unsupported model specified — returns model not found error","Malformed base64 encoding — returns decoding error","Insufficient funds or payment failure — returns payment required error","Empty or silent audio — may return empty transcript or low-confidence result"],"whenToPreferThis":"Choose this endpoint when you need to transcribe PCM WAV audio files (mono, 16-bit, 16 kHz) using a choice of AI models with live pricing transparency via OpenRouter. Ideal when you want model flexibility for speech-to-text without being locked into a single provider, or when you need to compare transcription quality and cost across models. Best suited for audio clips up to 10 minutes that can be base64-encoded.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T00:34:13.137Z","isFirstParty":false,"canonicalSlug":"openrouter-audio-transcriptions-16fad4d9"}