{"uid":"cap_CfGddU2XjcVC0nW8umKPN","slug":"cortexcloud-ai-speech-to-text-groq-whisper-93d3db00","name":"CortexCloud AI Speech-to-Text (Groq Whisper)","description":"OpenAI-compatible AI and data API for agents. Pay per call in USDC on Base via x402 — no API keys, no subscriptions, no lock-in.","url":"https://api.cortexcloud.org/x402/v1/audio/transcriptions","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"mime":{"type":"string"},"model":{"type":"string"},"audio_b64":{"type":"string"}}},"responseSchema":{"type":"object","format":"application/json","example":{}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ti08yv5lEZbBH4WHQ1jPv","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes audio to text using Groq-hosted Whisper, billed per call at $0.003 USDC via x402 micropayment protocol.","exampleAgentPrompt":"Can you transcribe this audio clip for me? It's a WAV file I've encoded in base64 — use the whisper-large-v3 model and return the text of what's being said.","exampleUseCases":[{"title":"Voice memo to meeting notes","prompt":"I recorded a voice memo of my meeting this morning — can you transcribe it into text? It's a base64-encoded MP3, use the Whisper model."},{"title":"Podcast interview transcription","prompt":"Here's a base64-encoded audio segment from a podcast interview in audio/mpeg format — can you run it through Whisper and give me the full transcript?"},{"title":"Multilingual customer call transcription","prompt":"I have a customer service call recording encoded in base64 as a WAV file — please transcribe it using whisper-large-v3 so I can review what was said."}],"resultDescription":"Returns a text transcription of the spoken audio content extracted from the provided base64-encoded audio file, generated by Groq-hosted Whisper.","failureModes":["Invalid or malformed base64 audio data returns an error","Unsupported MIME type results in a rejection response","Payment failure via x402 protocol blocks the request","Audio file too large or too long may cause timeout or rejection","Missing required fields (audio_b64, mime, model) return validation errors"],"whenToPreferThis":"Choose this endpoint when you need fast, pay-per-use speech-to-text transcription via Whisper without managing your own API keys or infrastructure. It is ideal for AI agents that operate on a per-call budget using USDC micropayments on Base, and for workloads where you want Groq's fast Whisper inference without a subscription or quota system.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":3,"lastUsedAt":"2026-08-05T13:49:31.140Z","lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:44:28.769Z","isFirstParty":false}