{"uid":"cap_2F0t9poi7xQ4Psv8d0sYF","slug":"tanod-audio-speech-translation-e6ffc850","name":"Tanod Audio Speech Translation","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.","url":"https://tanod.dev/v1/audio/translate-speech?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."},"speak":{"type":"boolean","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."},"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)."},"format":{"enum":["mp3","wav","ogg"],"type":"string","default":"mp3","description":"With speak: mp3, wav or ogg."},"output":{"enum":["base64","url"],"type":"string","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."},"target":{"enum":["en","es","fr","de","pt","it","nl","ru","zh","ja","ko","ar","hi","id","tl"],"type":"string","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)."},"language":{"anyOf":[{"type":"string","pattern":"^[a-z]{2,3}$"},{"type":"null"}],"default":null,"description":"Optional spoken language as an ISO 639-1 code. Default: detected."},"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. At most 2 minutes (45 seconds with speak)."},"include_transcript":{"type":"boolean","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."}}},"responseSchema":{"type":"json","example":{"audio":null,"engine":{"asr":{"id":"faster-whisper-base","source":"Systran/faster-whisper-base","compute":"int8","revision":"ebe41f70d5b6dfa9166e2c581c45c9c0cfc57b66"},"translate":"argos-translate (offline)"},"target":"fr","duration":10.7,"segments":[{"end":4.4,"text":"Bonjour, aujourd'hui je veux expliquer comment fonctionne notre service de traduction.","start":0},{"end":10.7,"text":"D'abord, vous envoyez un fichier audio, puis le système entend et écrit ce qu'il dit.","start":4.4}],"operation":"audio-translate-speech","timings_s":{"total":1.94,"decode":0.04,"translate":0.25,"speech_to_text":1.65},"truncated":false,"transcript":null,"input_bytes":879308,"translation":"Bonjour, aujourd'hui je veux expliquer comment fonctionne notre service de traduction. D'abord, vous envoyez un fichier audio, puis le système entend et écrit ce qu'il dit.","same_language":false,"source_language":"es","speech_truncated":false,"untrusted_content":true,"language_probability":0.9915}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_VxiOjGYP6gbccrBSrxSmB","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes speech from an audio file and translates it into a target language, optionally generating spoken audio of the translation.","exampleAgentPrompt":"I have a Spanish audio file at https://example.com/speech.mp3 — can you transcribe it and translate it into French, and also generate a spoken version of the translation using the ff_siwis voice as an mp3?","exampleUseCases":[{"title":"Translate foreign interview recording","prompt":"I have a recorded interview in Japanese at https://cdn.example.com/interview.mp3 — please transcribe and translate it into English so I can read what was said."},{"title":"Multilingual podcast clip translation","prompt":"Here's a podcast clip in Portuguese: https://media.example.com/podcast_pt.wav — translate it to Spanish and give me the spoken translation in the ef_dora voice as an mp3."},{"title":"Meeting notes from foreign language call","prompt":"I have an audio recording from our German-language team call at https://files.example.com/meeting_de.ogg — translate everything said into English and give me the full translated transcript with timestamps."}],"resultDescription":"Returns a JSON object containing the full translated text, detected source language, language probability, per-segment timestamps, operation timings, and optionally a base64-encoded or URL-linked audio file of the translation spoken aloud. Includes ASR and translation engine metadata.","failureModes":["Audio file exceeds 25 MB limit — rejected","Private, internal, or IP-literal host URLs refused","Unsupported target language specified — enum validation error","speak:true used with unsupported target language (only en/es/fr/hi/it/pt supported for TTS)","Audio too noisy or low quality — low language_probability and poor transcript","Translation truncated if spoken output exceeds 800 characters or 45 seconds","URL unreachable or returns non-audio content — fetch error"],"whenToPreferThis":"Choose this endpoint when you need to both transcribe speech from an audio file AND translate it to another language in a single call. It supports 15 target languages, provides per-segment timestamps, detects source language automatically, and optionally synthesizes the translated text as spoken audio using Kokoro TTS voices — making it ideal for multilingual audio workflows without requiring a separate STT + translation + TTS pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-16T03:07:33.988Z","isFirstParty":false,"canonicalSlug":"tanod-audio-speech-translation-e6ffc850"}