Models by Google
Gemini in Tõlk: 70+ languages, the speaker’s own voice.
Gemini Live Translate keeps the speaker’s voice and intonation in the translation and covers the widest language list in Tõlk. Gemini also recognizes stage speech and voices Studio recordings.
- Speech-to-speech
- Speech-to-text
- Text translation
- Text-to-speech
Models and how they run.
- Speech-to-speech
Gemini 3.5 Live Translate
gemini-3.5-live-translate-preview
One live session per language over the Gemini Live API.
- Speech-to-text
Gemini 3.5 Flash
gemini-3.5-flash
Stage recognition phrase by phrase, with your Dictionary in every request.
- Text translation
Gemini Pro and Flash
gemini-2.5-pro · gemini-2.5-flash
Studio translation models, picked per recipe.
- Text-to-speech
Gemini speech
gemini-2.5-flash-preview-tts
Studio voices for prepared recordings.
Why teams pick it
- Keeps the speaker’s own voice and intonation
- Widest live language list in Tõlk
- Target-language captions straight from the model
- Silent when the speaker already uses the listener’s language
Good to know
- Voice and speed follow the speaker; there is no voice picker.
- The live translation model is a Google preview model.
Languages
The widest live language list in Tõlk
From Afrikaans to Zulu, including Estonian, Latvian and Lithuanian, spoken directly in the speaker’s own voice.
Languages listeners can hear the translation in.
Gemini 3.5 Live TranslateSpeech-to-speech81 languages
- Afrikaans
- Akan
- Albanian
- Amharic
- Arabic
- Armenian
- Azerbaijani
- Basque
- Belarusian
- Bengali
- Bulgarian
- Burmese (Myanmar)
- Catalan
- Chinese
- Chinese (Simplified)
- Chinese (Traditional)
- Croatian
- Czech
- Danish
- Dutch
- English
- Estonian
- Filipino
- Finnish
- French
- Galician
- Georgian
- German
- Greek
- Gujarati
- Hausa
- Hebrew
- Hindi
- Hungarian
- Icelandic
- Indonesian
- Italian
- Japanese
- Javanese
- Kannada
- Kazakh
- Khmer
- Kinyarwanda
- Korean
- Lao
- Latvian
- Lithuanian
- Macedonian
- Malay
- Malayalam
- Marathi
- Mongolian
- Nepali
- Norwegian
- Norwegian (Bokmål)
- Persian
- Polish
- Portuguese
- Portuguese (Brazil)
- Portuguese (Portugal)
- Punjabi
- Romanian
- Russian
- Serbian
- Sindhi
- Sinhala
- Slovak
- Slovenian
- Spanish
- Sundanese
- Swahili
- Swedish
- Tamil
- Telugu
- Thai
- Turkish
- Ukrainian
- Urdu
- Uzbek
- Vietnamese
- Zulu
Tõlk shows which engines can serve each language when you set up an event.
Where Google Gemini works best.
No setup on your side
Google Gemini runs through Tõlk’s own accounts. You never connect a key, and if an engine has trouble, affected languages switch to a backup and back again on their own.
Google Gemini is a trademark of Google. Tõlk uses its models through Google’s public APIs; this is not a partnership or endorsement.
More of the mix
All routes and models
ElevenLabs
Studio-grade voices and fast speech recognition.
- Text-to-speech
- Speech-to-text
OpenAI
The default live interpreter, plus recognition, translation and voices.
- Speech-to-speech
- Speech-to-text
- Text translation
- Text-to-speech
Qwen
Live translation with bilingual captions and speaker labels.
- Speech-to-speech
Another model in mind? We’ll bring it in.
- Another providerA vendor or model you already use or trust.
- Open-source modelsOpen-weights speech, translation or voice models.
- Self-hostedModels on your own servers or private cloud.
The Live AI Translation Hub
Ready for your next moment?
Tell us what to make multilingual. We pilot it on your content, then you decide.