{"uid":"cap_dClWKN34sdXkOoUeUzsKN","slug":"tanod-audio-transcribe-e34358c8","name":"Tanod Audio Transcribe","description":"One MCP server and HTTP API with 193 pay-per-call tools for AI agents (security checks, chain data, finance, aviation, documents), plus free uptime and MikroTik monitoring and 130+ free browser tools. No signup; free daily tier. Operated by an AI.","url":"https://tanod.dev/v1/audio/transcribe?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"anyOf":[{"type":"string","maxLength":2048,"minLength":1},{"type":"null"}],"default":null,"description":"Public http(s) URL of the audio file (at most 25 MB; private, internal and IP-literal hosts are refused); or use file_base64."},"language":{"anyOf":[{"type":"string","pattern":"^[a-z]{2,3}$"},{"type":"null"}],"default":null,"description":"Optional spoken language as an ISO 639-1 code (en, es, fr, de, tl, ...). Default: detected from the first 30 seconds."},"file_base64":{"anyOf":[{"type":"string","maxLength":33398872,"minLength":1},{"type":"null"}],"default":null,"description":"The audio file as base64 (at most 25 MB decoded); or use url. MP3, WAV, FLAC, OGG, Opus, M4A/AAC, WebM and MP4 audio, detected from the content. At most 10 minutes."},"translate_to_english":{"type":"boolean","default":false,"description":"true: the text, segments, srt and vtt come out in English from any spoken language (Whisper translate task); `language` is still the spoken language. Default false: the text stays in the spoken language. Same price."}}},"responseSchema":{"type":"json","example":{"srt":"1\n00:00:00,000 --> 00:00:11,000\nAnd so my fellow Americans ask not what your country can do for you, ask what you can do for your country.\n\n","vtt":"WEBVTT\n\n00:00:00.000 --> 00:00:11.000\nAnd so my fellow Americans ask not what your country can do for you, ask what you can do for your country.\n\n","text":"And so my fellow Americans ask not what your country can do for you, ask what you can do for your country.","model":{"id":"faster-whisper-base","source":"Systran/faster-whisper-base","compute":"int8","revision":"ebe41f70d5b6dfa9166e2c581c45c9c0cfc57b66"},"duration":11,"language":"en","segments":[{"end":11,"text":"And so my fellow Americans ask not what your country can do for you, ask what you can do for your country.","start":0}],"operation":"audio-transcribe","truncated":false,"input_bytes":1152693,"untrusted_content":true,"language_probability":0.9528}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ZoRn7ENuXKdElHFdcmQvF","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes an audio file (via URL or base64) to plain text, SRT subtitles, and WebVTT captions with timestamps and segment data","exampleAgentPrompt":"Can you transcribe this audio file for me? Here's the URL: https://example.com/interview.mp3 — I need the full text transcript plus SRT subtitles, and the language should be English.","exampleUseCases":[{"title":"Podcast episode transcription","prompt":"I have a podcast episode at https://cdn.mypodcast.com/ep42.mp3 — can you transcribe it to text so I can turn it into a blog post? The language is English."},{"title":"Meeting recording subtitles","prompt":"Here's a base64-encoded WAV file of our team meeting — can you generate SRT subtitle captions from it with timestamps so we can add them to the recording?"},{"title":"Multilingual interview transcript","prompt":"I've got an audio file at https://storage.example.com/entrevista.ogg recorded in Spanish — can you transcribe it and give me both the plain text and the WebVTT captions?"}],"resultDescription":"Returns a JSON object containing: plain-text transcript, SRT-formatted subtitles, WebVTT-formatted captions, an array of segments each with start/end timestamps and text, detected or specified language code, language detection confidence probability, total audio duration in seconds, whether the audio was truncated, and the model details used (faster-whisper-base).","failureModes":["Audio URL exceeds 25 MB or audio is longer than 10 minutes — request rejected","Private, internal, or IP-literal host URLs are refused","Unsupported audio format — only MP3, WAV, FLAC, OGG, Opus, M4A/AAC, WebM, MP4 audio accepted","base64 payload exceeds 33 MB encoded size limit","Language code does not match ISO 639-1 pattern — validation error","Audio is too noisy or low quality for reliable transcription — low language_probability returned","Payment not provided or insufficient USDC — 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when you need a pay-per-call, no-signup audio transcription that returns plain text, SRT, and WebVTT simultaneously in one call, especially if you need timestamped segments. Ideal for AI agent workflows that process audio from public URLs or inline base64 payloads and need subtitle-ready output without managing a transcription service subscription.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-10T12:41:57.900Z","isFirstParty":false,"canonicalSlug":"tanod-audio-transcribe-e34358c8"}