Supported Languages
Audionotes.app Language Support
Audionotes supports 80+ languages with industry-leading accuracy powered by state-of-the-art AI models. We're continuously expanding our language library and enhancing transcription quality across all supported languages.
We use AI models such as OpenAI Whisper v3, Assembly AI Universal, Assembly AI Slam-1, Deepgram Nova 2, Google Gemini 2.5 Pro to achieve a very high level of accuracy.
Language Support & Accuracy Levels
All Supported Languages
English, Spanish, French, German, Indonesian, Italian, Japanese, Dutch, Polish, Portuguese, Russian, Turkish, Ukrainian, Catalan, Arabic, Azerbaijani, Bulgarian, Bosnian, Mandarin Chinese, Czech, Danish, Greek, Estonian, Finnish, Filipino, Galician, Hindi, Croatian, Hungarian, Korean, Macedonian, Malay, Norwegian Bokmål, Romanian, Slovak, Swedish, Thai, Urdu, Vietnamese, Afrikaans, Belarusian, Welsh, Persian (Farsi), Hebrew, Armenian, Icelandic, Kazakh, Lithuanian, Latvian, Māori, Marathi, Slovenian, Swahili, Tamil, Amharic, Assamese, Bengali, Gujarati, Hausa, Javanese, Georgian, Khmer, Kannada, Luxembourgish, Lingala, Lao, Malayalam, Mongolian, Maltese, Burmese, Nepali, Occitan, Punjabi, Pashto, Sindhi, Shona, Somali, Serbian, Telugu, Tajik, Uzbek, Yoruba
High accuracy (≤ 10% WER)
English, Spanish, French, German, Indonesian, Italian, Japanese, Dutch, Polish, Portuguese, Russian, Turkish, Ukrainian, Catalan
Good accuracy (>10% to ≤25% WER)
Arabic, Azerbaijani, Bulgarian, Bosnian, Mandarin Chinese, Czech, Danish, Greek, Estonian, Finnish, Filipino, Galician, Hindi, Croatian, Hungarian, Korean, Macedonian, Malay, Norwegian Bokmål, Romanian, Slovak, Swedish, Thai, Urdu, Vietnamese
Moderate accuracy (>25% to ≤50% WER)
Afrikaans, Belarusian, Welsh, Persian (Farsi), Hebrew, Armenian, Icelandic, Kazakh, Lithuanian, Latvian, Māori, Marathi, Slovenian, Swahili, Tamil
Fair accuracy (>50% WER)
Amharic, Assamese, Bengali, Gujarati, Hausa, Javanese, Georgian, Khmer, Kannada, Luxembourgish, Lingala, Lao, Malayalam, Mongolian, Maltese, Burmese, Nepali, Occitan, Punjabi, Pashto, Sindhi, Shona, Somali, Serbian, Telugu, Tajik, Uzbek, Yoruba
Language Detection & Settings
Smart Auto-Detection: Audionotes automatically identifies your spoken language, so you can start recording right away without manual setup.
Manual Override: Need more control? Set your preferred default language in settings for consistent transcription accuracy.
On Mobile :
On Web :
Language vs. Translation
Changing your language setting adjusts transcription recognition, it doesn't translate existing content. To get summaries or AI-generated content in different languages, adjust your output language in Settings or use the language selector in AI Create.
On Mobile :
On Web :
Important Note
While we strive for maximum accuracy, AI transcription may occasionally produce errors or unexpected results. We're committed to continuous improvement and appreciate your patience as we enhance our language capabilities.
Frequently Asked Questions
Audionotes supports 80+ languages including English, Spanish, French, German, Japanese, Chinese, Portuguese, Arabic, Russian, Hindi, Korean, Italian, Dutch, and many more. The full list is grouped above by accuracy tier.
Audionotes routes transcription requests across OpenAI Whisper v3, Assembly AI Universal, Deepgram Nova 2, and Google Gemini depending on the language and audio characteristics. The router picks the model with the highest published accuracy for each language.
Yes. The underlying speech models are trained on accent-diverse audio — for example, English handles American, British, Australian, Indian, Singaporean, Caribbean, and South African variants without you needing to flag the dialect. Spanish covers Iberian, Latin American, and US-Hispanic varieties.
Tier-1 languages (English, Spanish, French, German, Japanese, Chinese, Portuguese) reach up to 95% transcription accuracy under clear single-speaker conditions. Tier-2 languages (most other supported languages) typically reach 85–92%. Real-world accuracy varies with background noise, overlapping speech, and recording quality.
Yes. Audionotes auto-detects the spoken language per segment, so a recording that mixes (e.g.) English and Hindi will transcribe each segment in the right language. You can also pin a single language manually if you want to override auto-detection.
Yes — speaker diarization is on by default for all supported languages. Each speaker is labelled (Speaker 1, Speaker 2, …) in the transcript, and you can rename them in the editor.
Save time and stay organised with Audionotes
Without Audionotes
With Audionotes
Get the Audionotes app today
For desktop
Use Audionotes on web
For mobile
Scan the QR code below
Still not sure thatAudionotes.app isright for you?
Let ChatGPT, Claude, or Perplexity help you to choose.
Click a button and see what your favourite AI says about Audionotes.app.
