Fact · Languages and accents
45data points
The languages supported by speech recognition systems dataset holds 45 data points, each a published figure traced to its source.
Calculated from 45 data points on October 19, 2026
- How it is calculated
- Count of the published facts that are rows of the dataset: 45.
A statistic of the dataset How Many Languages Speech Recognition Supports, calculated by code from its published rows.
Calculated from
- Google says Gemini began rolling out on Android Auto globally in 45 languages.
- Amazon's developer page for the Alexa Voice Service says Alexa can interact with customers in 15 language and region entries, covering nine languages: English, German, Japanese, French, Italian, Spanish, Hindi, Portuguese and Arabic.
- The general Dictation section of Apple's iOS and iPadOS 27 feature availability page lists 63 language and region entries.
- AssemblyAI's documentation says its Universal-2 speech-to-text model supports 99 languages.
- AssemblyAI's documentation says its Universal-3.5 Pro speech-to-text model supports 18 languages, and that audio in other languages falls back to Universal-2 if the request asks for it.
- Google says Assistant voice typing is available in six languages: English, French, German, Italian, Japanese and Spanish.
- Amazon's Transcribe product page says its key features work across 100+ languages.
- NVIDIA's Canary 1B v2 supports speech transcription for 25 languages, and speech translation from English into 24 languages.
- Claude Code's voice dictation supports 20 languages, listed in its documentation from Czech to Ukrainian.
- Claude's mobile help article lists 12 languages for dictation on iOS and Android.
- Deepgram's Nova-3 model language table lists 60 languages, counting the three Chinese variants as one language and German (Switzerland) as a German variant. Deepgram states no total.
- ElevenLabs' speech-to-text documentation says its Scribe v2 model supports 90 or more languages, and lists them with their codes.
- Google's Gboard help lists six languages for advanced voice typing with automatic language switching: English, French, German, Italian, Japanese and Spanish.
- Google's developer reference for the Google Assistant Service lists 14 language and region codes that its speech recognition engine can understand, covering 8 languages.
- Google says Google Assistant on Google TV devices is available in 14 languages, including English, French, German, Spanish, Italian, Japanese, Hindi, Chinese (Traditional), Korean, Portuguese (Brazil), Dutch, Norwegian, Swedish and Danish.
- Google Cloud's Speech-to-Text product page says the service supports over 125 languages.
- Heidi's Dictate product page says the tool is ready from a user's first visit and works in more than 90 languages.
- The IndicVoices authors built IndicASR, which they describe as the first speech recognition model to support all 22 languages in the Eighth Schedule of the Indian Constitution.
- Apple's iOS feature availability table lists 48 language and regional variants for On-Device and Modeless Dictation.
- Apple's macOS feature availability page lists 63 language and regional variants for Dictation on the Mac.
- Apple lists 48 language and regional variants for on-device and modeless Dictation on the Mac, which require a download of speech models.
- Apple lists 20 language and regional variants for Voice Control on the Mac, about a third of the number for Dictation.
- Meta's mms-1b-all checkpoint, on its Hugging Face model card, supports 1162 languages for speech recognition.
- Microsoft's Azure Speech product page says its audio captioning works in more than 100 languages.
- Meta's Massively Multilingual Speech project built a single multilingual speech recognition model for 1,107 languages.
- Nuance's release notes for Dragon Professional Individual 15.6.1 say the full build is supported for six languages: ENX, DEU, FRA, ITA, ESP and NLD (English, German, French, Italian, Spanish and Dutch).
- Meta's Omnilingual ASR is an open-source speech recognition model family for more than 1,600 languages.
- OpenAI's speech to text guide says Whisper supports 98 languages, and that accuracy varies by language.
- NVIDIA says the parakeet-tdt-0.6b-v3 model extends language support from English to 25 European languages.
- Samsung's UAE Transcript Assist page lists 13 languages for transcription and transformation.
- Samsung's US Voice Recorder page lists 16 languages for Transcript assist, including several regional forms of English, Spanish and Portuguese.
- Meta's SeamlessM4T is a single model that supports speech-to-text translation and speech recognition for up to 100 languages.
- Speechmatics' documentation lists its transcription languages, and counting the table's single-language rows (not the auto option or the seven bilingual and multi-language packs) gives 55 languages for the Enhanced and Standard models.
- Microsoft lists 15 languages and dialects for Voice Access in Windows 11: six English variants, two Spanish, German, two French, Simplified and Traditional Chinese, Japanese and Italian.
- Microsoft's Voice access command list says Voice access is available in six languages: English, Spanish, French, German, Chinese and Japanese.
- Microsoft's Voice Access FAQ says the feature is currently available in English, Spanish, French and German, which is four languages.
- The Vosk project says it supports more than 20 languages and dialects, with English, Indian English, German and French among them.
- Mistral says Voxtral Mini Transcribe V2 transcribes in 13 languages, with speaker diarization, context biasing and word-level timestamps.
- Mistral says Voxtral Realtime is natively multilingual and transcribes in 13 languages: English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian and Dutch.
- WebKit says Safari's speech recognition, powered by the Siri engine, gives high-quality transcription for over 50 languages and dialects.
- The Whisper paper says its model predicts the spoken language with one token for each language in its training set, and that there are 99 such tokens, so the training data covers 99 languages.
- Windows 10 dictation accepts speech in 13 language variants, US English plus 12 that Microsoft lists for basic text, symbols, letters and numbers, but its dictation commands work only in US English.
- Microsoft's Windows 11 voice typing article lists 46 languages and locales that support voice typing, from Bulgarian to Vietnamese.
- Microsoft says Windows Speech Recognition is available only in English (United States, United Kingdom, Canada, India and Australia), French, German, Japanese, Mandarin (Simplified and Traditional Chinese) and Spanish, 11 variants in all.
- Microsoft's Dictate in Word article lists 15 main supported languages and locales, from Chinese (China) to Spanish (Mexico), with a separate list of preview languages.