Speech to text · Languages
AudioPod transcribes 100 languages: pick one in the language menu (or send its ISO code to the API) or leave auto-detect on. Speaker labels are available for English, Spanish, French, German, Portuguese, Russian, Arabic, Hindi, Japanese, Korean and Chinese. Every language costs 220 credits a minute.
Last updated
| Language | Code | Speaker labels | Note |
|---|---|---|---|
| English | en | Yes | One code, en, covers every English accent. For short clips, set the language explicitly instead of relying on auto-detect, which has little audio to work from. |
| Spanish (Español) | es | Yes | One code, es, covers Spain and Latin America. Catalan (ca), Galician (gl) and Basque (eu) have their own codes — pick those for recordings in those languages. |
| French (Français) | fr | Yes | One code, fr, covers France, Canada, Belgium and Switzerland. Breton (br) and Occitan (oc) are separate codes. |
| German (Deutsch) | de | Yes | One code, de, covers Germany, Austria and Switzerland. Luxembourgish (lb) has its own code. |
| Portuguese (Português) | pt | Yes | One code, pt, covers Brazil and Portugal. Galician (gl), close to Portuguese, has its own code. |
| Russian (Русский) | ru | Yes | Russian recordings use ru; Ukrainian (uk) and Belarusian (be) have their own codes, so set the language explicitly for those closely related languages. |
| Arabic (العربية) | ar | Yes | Arabic transcripts and subtitles read right to left; SRT and VTT store the text in reading order, so check that your video player renders right-to-left captions. |
| Hindi (हिन्दी) | hi | Yes | Everyday Hindi often mixes in English words; set the language to Hindi when Hindi carries most of the conversation. |
| Japanese (日本語) | ja | Yes | Japanese has no spaces between words, so subtitle lines are measured in characters. As a guide, Netflix's Japanese style guide caps a line at 13 full-width characters; AudioPod's export does not wrap cues to that limit, so adjust line breaks in your subtitle editor. |
| Korean (한국어) | ko | Yes | Korean subtitle lines are measured in characters. As a guide, Netflix's Korean style guide caps a line at 16 characters; AudioPod's export does not wrap cues to that limit, so adjust line breaks in your subtitle editor. |
| Chinese (中文) | zh | Yes | Mandarin uses zh; Cantonese has its own code, yue — choose it for Cantonese recordings, transcribed without speaker labels. |
Transcription with timestamps and every export format; transcribe these without speaker labels.
| Language | Code |
|---|---|
| Afrikaans | af |
| Albanian | sq |
| Amharic | am |
| Armenian | hy |
| Assamese | as |
| Azerbaijani | az |
| Bashkir | ba |
| Basque | eu |
| Belarusian | be |
| Bengali | bn |
| Bosnian | bs |
| Breton | br |
| Bulgarian | bg |
| Burmese | my |
| Cantonese | yue |
| Catalan | ca |
| Croatian | hr |
| Czech | cs |
| Danish | da |
| Dutch | nl |
| Estonian | et |
| Faroese | fo |
| Finnish | fi |
| Galician | gl |
| Georgian | ka |
| Greek | el |
| Gujarati | gu |
| Haitian Creole | ht |
| Hausa | ha |
| Hawaiian | haw |
| Hebrew | he |
| Hungarian | hu |
| Icelandic | is |
| Indonesian | id |
| Italian | it |
| Javanese | jv |
| Kannada | kn |
| Kazakh | kk |
| Khmer | km |
| Lao | lo |
| Latin | la |
| Latvian | lv |
| Lingala | ln |
| Lithuanian | lt |
| Luxembourgish | lb |
| Macedonian | mk |
| Malagasy | mg |
| Malay | ms |
| Malayalam | ml |
| Maltese | mt |
| Maori | mi |
| Marathi | mr |
| Mongolian | mn |
| Nepali | ne |
| Norwegian | no |
| Norwegian Nynorsk | nn |
| Occitan | oc |
| Pashto | ps |
| Persian | fa |
| Polish | pl |
| Punjabi | pa |
| Romanian | ro |
| Sanskrit | sa |
| Serbian | sr |
| Shona | sn |
| Sindhi | sd |
| Sinhala | si |
| Slovak | sk |
| Slovenian | sl |
| Somali | so |
| Sundanese | su |
| Swahili | sw |
| Swedish | sv |
| Tagalog | tl |
| Tajik | tg |
| Tamil | ta |
| Tatar | tt |
| Telugu | te |
| Thai | th |
| Tibetan | bo |
| Turkish | tr |
| Turkmen | tk |
| Ukrainian | uk |
| Urdu | ur |
| Uzbek | uz |
| Vietnamese | vi |
| Welsh | cy |
| Yiddish | yi |
| Yoruba | yo |
Upload up to 10 files (up to 1 GB each) or paste a YouTube link in Speech to Text.
Pick it from the menu (API: language="<code>") or leave auto-detect on; set it explicitly for short clips.
Turn them on for multi-speaker recordings in the languages listed with speaker labels.
Fix names in the editor, then download TXT, JSON, SRT, VTT, DOCX, PDF, HTML.