Languages Support
Transcribe audio in 98+ languages with automatic detection or manual specification.
Automatic Detection
Leave the language parameter empty and our models will automatically detect the spoken language.
# Auto-detect language
response = requests.post(
"https://yourvoic.com/api/v1/stt/transcribe",
headers={"X-API-Key": "your_api_key"},
files={"file": open("audio.mp3", "rb")},
data={"model": "cipher-fast"} # No language specified
)
Manual Language Specification
For better accuracy, specify the language using ISO 639-1 codes:
# Specify language
response = requests.post(
"https://yourvoic.com/api/v1/stt/transcribe",
headers={"X-API-Key": "your_api_key"},
files={"file": open("audio.mp3", "rb")},
data={
"model": "cipher-fast",
"language": "es" # Spanish
}
)
Cipher Models - Supported Languages (90 Languages)
Cipher models support transcription in 90 languages with automatic language detection and translation to English.
| Language | Code | Language | Code |
|---|---|---|---|
| Afrikaans | af | Albanian | sq |
| Amharic | am | Arabic | ar |
| Armenian | hy | Assamese | as |
| Azerbaijani | az | Basque | eu |
| Belarusian | be | Bengali | bn |
| Bosnian | bs | Bulgarian | bg |
| Burmese | my | Cantonese | yue |
| Catalan | ca | Chinese | zh |
| Croatian | hr | Czech | cs |
| Danish | da | Dutch | nl |
| English | en | Estonian | et |
| Finnish | fi | French | fr |
| Galician | gl | Georgian | ka |
| German | de | Greek | el |
| Gujarati | gu | Hausa | ha |
| Hebrew | he | Hindi | hi |
| Hungarian | hu | Icelandic | is |
| Indonesian | id | Italian | it |
| Japanese | ja | Javanese | jw |
| Kannada | kn | Kazakh | kk |
| Khmer | km | Korean | ko |
| Lao | lo | Latvian | lv |
| Lithuanian | lt | Macedonian | mk |
| Malagasy | mg | Malay | ms |
| Malayalam | ml | Marathi | mr |
| Mongolian | mn | Nepali | ne |
| Norwegian | no | Pashto | ps |
| Persian | fa | Polish | pl |
| Portuguese | pt | Punjabi | pa |
| Romanian | ro | Russian | ru |
| Serbian | sr | Sindhi | sd |
| Sinhala | si | Slovak | sk |
| Slovenian | sl | Somali | so |
| Spanish | es | Sundanese | su |
| Swahili | sw | Swedish | sv |
| Tagalog | tl | Tajik | tg |
| Tamil | ta | Tatar | tt |
| Telugu | te | Thai | th |
| Turkish | tr | Turkmen | tk |
| Ukrainian | uk | Urdu | ur |
| Uzbek | uz | Vietnamese | vi |
| Welsh | cy | Yiddish | yi |
| Yoruba | yo |
Lucid Models - Supported Languages (36 Languages)
Lucid models provide high-accuracy transcription with real-time streaming support for 36 languages.
| Language | Code | Regional Variants |
|---|---|---|
| Chinese | zh | zh-CN, zh-TW, zh-HK |
| Danish | da | da-DK |
| Dutch | nl | nl-NL, nl-BE |
| English | en | en-US, en-GB, en-AU, en-NZ, en-IN |
| Flemish | nl-BE | - |
| French | fr | fr-FR, fr-CA |
| German | de | de-DE, de-AT, de-CH |
| Hindi | hi | hi-IN, hi-Latn |
| Indonesian | id | id-ID |
| Italian | it | it-IT |
| Japanese | ja | ja-JP |
| Korean | ko | ko-KR |
| Norwegian | no | no-NO |
| Polish | pl | pl-PL |
| Portuguese | pt | pt-BR, pt-PT |
| Russian | ru | ru-RU |
| Spanish | es | es-ES, es-419 (Latin America) |
| Swedish | sv | sv-SE |
| Tamil | ta | ta-IN |
| Tatar | tt | - |
| Turkish | tr | tr-TR |
| Ukrainian | uk | uk-UA |
Lucid Multi-Language Support
The lucid-multi model supports these additional languages for multilingual transcription:
| Language | Code | Language | Code |
|---|---|---|---|
| Bulgarian | bg | Catalan | ca |
| Czech | cs | Estonian | et |
| Finnish | fi | Greek | el |
| Hungarian | hu | Latvian | lv |
| Lithuanian | lt | Malay | ms |
| Romanian | ro | Slovak | sk |
| Thai | th | Vietnamese | vi |
Language Comparison by Model
| Feature | Cipher Models | Lucid Models |
|---|---|---|
| Total Languages | 90 | 36 (50+ with lucid-multi) |
| Auto-Detection | ✅ | ✅ |
| Regional Variants | Limited | Extensive |
| Translation to English | ✅ (cipher-fast) | ❌ |
| Code-Switching | ❌ | ✅ (lucid-multi) |
| Real-time Streaming | ❌ | ✅ |
Multilingual Content
For audio containing multiple languages, use lucid-multi which supports code-switching:
# Multilingual transcription
response = requests.post(
"https://yourvoic.com/api/v1/stt/lucid/transcribe",
headers={"X-API-Key": "your_api_key"},
files={"file": open("multilingual_meeting.mp3", "rb")},
data={"model": "lucid-multi"}
)
Translation (Cipher Models Only)
Cipher-fast model supports translation of any supported language to English:
# Translate audio to English
response = requests.post(
"https://yourvoic.com/api/v1/stt/cipher/transcribe",
headers={"X-API-Key": "your_api_key"},
files={"file": open("spanish_audio.mp3", "rb")},
data={
"model": "cipher-fast",
"task": "translate" # Translates to English
}
)
💡 Tip: For best accuracy, always specify the language if you know it beforehand. Auto-detection adds a small processing overhead.