# Audio Translator: Translate Audio and Video to Text Translate audio or video speech into English or 60 languages as readable text and SRT or VTT subtitles. ## How it works 1. Add an MP3, voice memo, interview recording, or video file. 2. Choose the target language you want to read (such as English) and optionally set the spoken source language. 3. Press Translate audio, read the translation, and download TXT, SRT, or VTT subtitles. ## A written translation timed to your recording Audo's online audio translator turns speech from audio (MP3, WAV, M4A, FLAC, OGG, AAC, Opus, WebM) and video (MP4, MOV, MKV, WebM, AVI) files up to 2 GB into written text and subtitles across 60 languages, with the first 2 minutes free, 3 times a day, and no sign-up. Whether you need to translate audio to English from a foreign-language interview or prepare translated SRT subtitles for a global video audience, every passage stays linked to its place on the timeline. Instead of pasting an un-timed wall of text into a separate translator and losing track of who spoke when, Audo translates segment by segment so your SRT and VTT downloads line up with the recording right away. If you want a transcript in the same language that was spoken rather than a translation, use Transcribe audio. Tool: Translate audio (`translate_transcript`). The same tool's other pages: https://audo.ai/translate-spanish-to-english-audio.md. Price: 5 credits a minute — $0.05/min ($3.00/hr), with no subscription — of input for whole files, charged only when a job succeeds. ## Free API ```bash curl -F file=@interview.mp3 -F target_language=en -F format=srt https://audo.ai/api/try/audio-translator -D response.headers -o response.body ``` Read response.headers and response.body before naming media. Handle 202, 200 JSON and errors with the complete response client at https://audo.ai/docs/api?utm_source=markdown&utm_medium=agent#responses. Free for the first 2 minutes of each file, 3 times a day per person, with no key or account. Uploads up to 10 GB, 2 at once from one address. The response is the result itself; a job that runs longer than about 30 seconds returns 202 with a link to check on it. With an API key (`-H "Authorization: Bearer $AUDO_API_KEY"`), omitting free runs the whole file with credits if the balance covers it, otherwise the free portion if quota remains. Set free=true to prohibit spending; for paid whole files use free=false with an approved positive max_credits. A free result cut short comes with finishUrl (and the Audo-Finish-Url header when the response is the file itself): give it to the person, who pays there (from $5, no sign-up), and the whole file runs; keep checking the status link, whose finishedBy names the whole-file job and its own status link. Details: https://audo.ai/docs/api.md ## Options Form fields with the same names as the MCP tool's inputs: - `target_language`: Translate into this language code, such as en, es, or ja. - `source_language`: The spoken language. Default: detected, or the supplied transcript's language. - `format`: what the free API returns: json (default), srt, vtt, or txt. ## Languages 60 languages, detected automatically: `af` Afrikaans, `ar` Arabic, `hy` Armenian, `as` Assamese, `az` Azerbaijani, `bn` Bengali, `bs` Bosnian, `bg` Bulgarian, `yue` Cantonese, `ca` Catalan, `zh` Chinese (Simplified), `cs` Czech, `da` Danish, `nl` Dutch, `en` English, `et` Estonian, `fil` Filipino, `fi` Finnish, `fr` French, `gl` Galician, `de` German, `el` Greek, `gu` Gujarati, `he` Hebrew, `hi` Hindi, `hu` Hungarian, `is` Icelandic, `id` Indonesian, `it` Italian, `ja` Japanese, `kn` Kannada, `kk` Kazakh, `ko` Korean, `lv` Latvian, `lt` Lithuanian, `mk` Macedonian, `ms` Malay, `ml` Malayalam, `mr` Marathi, `ne` Nepali, `nb` Norwegian Bokmål, `or` Odia, `fa` Persian, `pl` Polish, `pt` Portuguese, `pa` Punjabi, `ro` Romanian, `ru` Russian, `sk` Slovak, `sl` Slovenian, `es` Spanish, `sw` Swahili, `sv` Swedish, `ta` Tamil, `te` Telugu, `th` Thai, `tr` Turkish, `uk` Ukrainian, `ur` Urdu, `vi` Vietnamese. ## From an assistant (MCP) Add https://audo.ai/mcp and sign in (setup for each assistant: https://audo.ai/setup.md). The tool is `translate_transcript`: > Translates speech into another language, keeping each transcript segment's times, speakers, and order. Use it for translated text and subtitles. Reuses transcript_file_id or transcribes the recording first. It costs 5 credits a minute, or 2 with transcript_file_id, charged only if the job succeeds. Returns translated JSON, SRT, VTT, and TXT download links with approximate word times, or job_id for get_job if it takes longer. Example: "Use Audo to translate interview.mp3 into English text and subtitles." ## Questions **Is audio translation free?** Audo translates the first 2 minutes free, 3 times a day. Whole recordings cost $0.05 a minute ($3.00 an hour), with no subscription. See pricing for packs. **How do I translate audio to English or another language?** Add your recording above, leave the destination language set to English (or pick any of the 60 supported languages), and press Translate audio. Audo transcribes the spoken words and translates each segment into written text, SRT captions, and VTT subtitles while keeping the original timestamps. **Can I use this as a video translator for subtitles?** Yes. Upload an MP4, MOV, MKV, WebM, or AVI video that contains speech, and Audo translates the soundtrack into timed SRT and VTT subtitle files. Because every translated caption stays aligned to the original video timeline, you can drop the SRT straight into your video editor or YouTube upload. **Which download format should I choose: TXT, SRT, or VTT?** Download TXT when you want a clean written translation to read, quote, or share in notes. Choose SRT when uploading translated subtitles to YouTube, LinkedIn, or a desktop editor, and VTT for web video players. You also get the segment-by-segment JSON transcript. **Will translated captions match the exact timing of the speaker?** Each translated segment keeps the exact start and end time of the original spoken phrase, while individual word times are distributed across the segment as an approximation. Because sentence order and length change between languages, review fast exchanges, names, and line breaks before publishing. **Does this replace the speaker's voice with a dubbed audio track?** No. This page produces written translations and timed subtitle files so viewers can read along in their language while hearing the original speaker. It does not synthesize a new voice or alter your audio file. ## More - Every tool: https://audo.ai/llms.txt - OpenAPI: https://audo.ai/api/openapi.json - This page for people: https://audo.ai/audio-translator?utm_source=markdown&utm_medium=agent