{"slug":"tanod-dev-v1-audio-translate-speech-ba76c3","title":"mlpeek (Tanod) speech translation","host":"tanod.dev","method":"POST","resource":"https://tanod.dev/v1/audio/translate-speech","category":"image","description":"mlpeek (Tanod) speech translation: an audio file of up to 2 minutes as translated text in English or 14 languages with timed segments, optionally spoken (Whisper, Argos, Kokoro). Use when an agent must turn speech in another language into translated text or spoken audio, from a 2-minute clip.","price_listed":0.02,"price_asked":0.02,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":204,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:137","eip155:42161","eip155:56","eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"target":"es","url":"https://tanod.dev/samples/speech-sample.mp3"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"file_base64":{"anyOf":[{"maxLength":33398872,"minLength":1,"type":"string"},{"type":"null"}],"default":null,"description":"The audio file as base64 (at most 25 MB decoded); or use url. At most 2 minutes (45 seconds with speak)."},"format":{"default":"mp3","description":"With speak: mp3, wav or ogg.","enum":["mp3","wav","ogg"],"type":"string"},"include_transcript":{"default":false,"description":"true adds `transcript` in the spoken language with a second Whisper pass (about doubles the speech-to-text time). English audio always returns it.","type":"boolean"},"language":{"anyOf":[{"pattern":"^[a-z]{2,3}$","type":"string"},{"type":"null"}],"default":null,"description":"Optional spoken language as an ISO 639-1 code. Default: detected."},"output":{"default":"base64","description":"base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window.","enum":["base64","url"],"type":"string"},"speak":{"default":false,"description":"true adds `audio`, the translation spoken (Kokoro). Targets en, es, fr, hi, it and pt only; the clip is limited to 45 seconds and at most 800 characters are spoken.","type":"boolean"},"target":{"description":"Language of the translation: en (one Whisper pass) or es, fr, de, pt, it, nl, ru, zh, ja, ko, ar, hi, id, tl (Whisper to English, then English to the target).","enum":["en","es","fr","de","pt","it","nl","ru","zh","ja","ko","ar","hi","id","tl"],"type":"string"},"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."},"voice":{"anyOf":[{"enum":["af_heart","af_alloy","af_aoede","af_bella","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","am_santa","bf_alice","bf_emma","bf_isabella","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis","ef_dora","em_alex","em_santa","ff_siwis","hf_alpha","hf_beta","hm_omega","hm_psi","if_sara","im_nicola","pf_dora","pm_alex","pm_santa"],"type":"string"},{"type":"null"}],"default":null,"description":"With speak: a voice for the target language (default af_heart en, ef_dora es, ff_siwis fr, hf_alpha hi, if_sara it, pf_dora pt)."}},"required":["target"],"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":{"description":"Abridged to fit the header. Full example: the 402 JSON body. Full schema: https://tanod.dev/openapi.json POST /v1/audio/translate-speech","type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-18","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.02,"price_match":true,"latency_ms":204,"error":null}],"description_full":"mlpeek (Tanod) speech translation: an audio file of up to 2 minutes as translated text in English or 14 languages with timed segments, optionally spoken (Whisper, Argos, Kokoro). Use when an agent must turn speech in another language into translated text or spoken audio, from a 2-minute clip.","last_updated":"2026-10-13T20:38:05.596Z","schemes":["exact"]}