{"slug":"tanod-dev-v1-audio-transcribe-fb6342","title":"mlpeek (Tanod) speech to text and subtitles","host":"tanod.dev","method":"POST","resource":"https://tanod.dev/v1/audio/transcribe","category":"image","description":"mlpeek (Tanod) speech to text and subtitles: an audio file of up to 10 minutes as text, timed segments, SRT and WebVTT (faster-whisper). Use when an agent must turn a spoken-audio file of up to 10 minutes into text, timed segments or SRT captions.","price_listed":0.01,"price_asked":0.01,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":219,"reported_calls_30d":2,"reported_payers_30d":2,"networks":["eip155:137","eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"url":"https://tanod.dev/samples/speech-sample.mp3"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"file_base64":{"anyOf":[{"maxLength":33398872,"minLength":1,"type":"string"},{"type":"null"}],"default":null,"description":"The audio file as base64 (at most 25 MB decoded); or use url. MP3, WAV, FLAC, OGG, Opus, M4A/AAC, WebM and MP4 audio, detected from the content. At most 10 minutes."},"language":{"anyOf":[{"pattern":"^[a-z]{2,3}$","type":"string"},{"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."},"url":{"anyOf":[{"maxLength":2048,"minLength":1,"type":"string"},{"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."}},"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"duration":{"type":"number"},"input_bytes":{"type":"integer"},"language":{"type":"string"},"language_probability":{"type":"number"},"model":{"properties":{"compute":{"type":"string"},"id":{"type":"string"},"revision":{"type":"string"},"source":{"type":"string"}},"type":"object"},"operation":{"type":"string"},"segments":{"items":{"properties":{"end":{"type":"number"},"start":{"type":"number"},"text":{"type":"string"}},"required":["start","end","text"],"type":"object"},"type":"array"},"srt":{"type":"string"},"text":{"type":"string"},"truncated":{"type":"boolean"},"untrusted_content":{"type":"boolean"},"vtt":{"type":"string"}},"required":["operation","text","language","duration","segments","srt","vtt","untrusted_content"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-10","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":219,"error":null}],"description_full":"mlpeek (Tanod) speech to text and subtitles: an audio file of up to 10 minutes as text, timed segments, SRT and WebVTT (faster-whisper). Use when an agent must turn a spoken-audio file of up to 10 minutes into text, timed segments or SRT captions.","last_updated":"2026-10-09T19:53:04.26Z","schemes":["exact"]}