{"success":true,"data":{"id":"svc_audio_transcribe_01","slug":"audio-transcribe","name":"Speech to Text (Whisper Transcription)","description":"Speech to text for agents: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detection. Runs OpenAI Whisper (small by default, base for speed) on agentsvc.io itself, the audio is deleted after the call. Send audio_url or audio_base64 (mp3, mp4, m4a, wav, ogg, webm, flac), up to 10 minutes and 24 MB per call. Returns text, detected language, duration and segments with start and end seconds. Also available OpenAI-compatible at POST /v1/audio/transcriptions (multipart file, model whisper-1).","category":"text","endpoint":"https://agentsvc.io/api/v1/proxy/audio-transcribe","price_usdc":0.01,"latency_p99_ms":60000,"input_schema":{"type":"object","properties":{"audio_url":{"type":"string","description":"Public URL of the audio file"},"audio_base64":{"type":"string","description":"Audio file as base64; or use audio_url"},"language":{"type":"string","description":"ISO 639-1 code like en or de, default auto-detect"},"model":{"type":"string","enum":["small","base"],"default":"small","description":"small is more accurate, base about twice as fast"},"timestamps":{"type":"boolean","default":true,"description":"Include segments with start and end seconds"}}},"output_schema":{"type":"object","properties":{"text":{"type":"string"},"language":{"type":"string"},"language_probability":{"type":"number"},"duration_seconds":{"type":"number"},"model":{"type":"string"},"processing_ms":{"type":"integer"},"segments":{"type":"array","items":{"type":"object","properties":{"start":{"type":"number"},"end":{"type":"number"},"text":{"type":"string"}}}},"model_license":{"type":"string"}},"required":["text","language","duration_seconds"],"example":{"text":"This is a sample recording for the agents.io speech to text service. It turns spoken audio into text with time stamps in about 100 languages.","language":"en","language_probability":0.998,"duration_seconds":9.17,"model":"whisper-small","processing_ms":3688,"segments":[{"start":0,"end":4.4,"text":"This is a sample recording for the agents.io speech to text service."},{"start":4.4,"end":9,"text":"It turns spoken audio into text with time stamps in about 100 languages."}],"model_license":"MIT (OpenAI Whisper weights, faster-whisper runtime), runs on agentsvc.io, audio is deleted after the call"}},"is_active":true,"provider":"agentsvc.io","tags":["speech-to-text","transcription","whisper","audio","voice"],"method":"POST","example_input":{"audio_url":"https://agentsvc.io/samples/speech-en.mp3"},"price_atomic":"10000","price_display":"$0.01 USDC","try_url":"https://agentsvc.io/api/v1/try/audio-transcribe","try_limit_per_day":3,"info_url":"https://agentsvc.io/api/v1/services/audio-transcribe","page_url":"https://agentsvc.io/services/audio-transcribe","curl_example":"curl -X POST https://agentsvc.io/api/v1/proxy/audio-transcribe -H \"Content-Type: application/json\" -d '{\"audio_url\":\"https://agentsvc.io/samples/speech-en.mp3\"}'","status":{"ok":true,"latency_ms":4719,"checked_at":"2026-10-15T12:29:36.797Z"}},"payment":{"protocol":"x402","x402_versions_accepted":[1,2],"scheme":"exact","network":"eip155:8453","network_v1":"base","chain_id":8453,"asset":"USDC","asset_contract":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","asset_decimals":6,"eip712_domain":{"name":"USD Coin","version":"2","chainId":8453,"verifyingContract":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913"},"pay_to":"0x622efA6Ceb83a5b6EdBC931332f4db68B7f74F27","facilitator":"https://api.cdp.coinbase.com/platform/v2/x402","request_header_v2":"PAYMENT-SIGNATURE","request_header_v1":"X-PAYMENT","requirements_v2":"base64 JSON in the PAYMENT-REQUIRED response header of the 402","requirements_v1":"JSON body of the 402 (accepts[0])","receipt_header":"PAYMENT-RESPONSE (and X-PAYMENT-RESPONSE): base64 JSON with transaction hash","accounts_required":false,"api_keys_required":false,"settlement":"per call, on-chain, after the service succeeded. Failed calls are never charged.","also_accepted":[{"network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","network_v1":"solana","asset":"USDC","asset_mint":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","pay_to":"5JzPS5qpEwUM1vTC9GG7uqvwJdHzbEwfoPHf2Ki977tg","note":"Solana option is accepts[1] in the 402. The facilitator pays the transaction fee (extra.feePayer); the payer needs only USDC, no SOL."}]},"links":{"catalog":"https://agentsvc.io/api/v1/services","payment_requirements":"https://agentsvc.io/api/v1/payment-requirements","credits":"https://agentsvc.io/api/v1/credits","openapi":"https://agentsvc.io/openapi.json","llms_txt":"https://agentsvc.io/llms.txt","llms_full_txt":"https://agentsvc.io/llms-full.txt","agents_md":"https://agentsvc.io/AGENTS.md","skill_md":"https://agentsvc.io/SKILL.md","status":"https://agentsvc.io/api/v1/status","docs":"https://agentsvc.io/docs","mcp_server":"https://agentsvc.io/mcp-server.mjs","discovery":"https://agentsvc.io/.well-known/x402","agent_card":"https://agentsvc.io/.well-known/agent-card.json"}}