Models by ElevenLabs
ElevenLabs in Tõlk: studio-grade voices, live and prepared.
ElevenLabs voices read translations on Dictionary-assisted and studio-voice routes, live and in Studio’s Premium packs. Scribe recognizes stage speech word by word.
- Text-to-speech
- Speech-to-text
Models and how they run.
- Text-to-speech
Eleven v4 Turbo
eleven_v4_turbo
Streams each translated phrase in a chosen voice, live.
- Text-to-speech
Premium studio voices
eleven_v4_turbo
A voice per speaker in Studio’s Premium band.
- Speech-to-text
Scribe v2 Realtime
scribe_v2_realtime
Stage recognition word by word, with Dictionary key terms.
- Speech-to-text
Scribe v2
scribe_v2
Transcribes uploaded recordings for Studio.
Why teams pick it
- Natural, expressive voices
- A consistent voice per speaker
- Speed control live, with catch-up when the speaker races
- Read-as hints from your Dictionary shape pronunciation
Good to know
- Speech → text → speech adds a little delay over direct translation.
- Voices come from a curated ElevenLabs set, chosen per language or speaker.
Languages
Studio-grade voices across the Eleven v4 list
Scribe hears more than 90 languages; Eleven v4 Turbo voices speak the translations, including Estonian, Latvian, Russian and Hebrew.
Languages listeners can hear the translation in.
Eleven v4 TurboSpeech → text → speech72 languages
- Afrikaans
- Amharic
- Arabic
- Armenian
- Azerbaijani
- Belarusian
- Bengali
- Bulgarian
- Burmese (Myanmar)
- Catalan
- Chinese
- Chinese (Simplified)
- 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
- Korean
- Lao
- Latvian
- Lithuanian
- Macedonian
- Malay
- Malayalam
- Marathi
- Mongolian
- Nepali
- Norwegian
- Norwegian (Bokmål)
- Persian
- Polish
- Portuguese
- Portuguese (Brazil)
- Punjabi
- Romanian
- Russian
- Serbian
- Sindhi
- Slovak
- Slovenian
- Spanish
- 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 ElevenLabs works best.
No setup on your side
ElevenLabs 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.
ElevenLabs is a trademark of ElevenLabs. Tõlk uses its models through ElevenLabs’s public APIs; this is not a partnership or endorsement.
More of the mix
All routes and models
OpenAI
The default live interpreter, plus recognition, translation and voices.
- Speech-to-speech
- Speech-to-text
- Text translation
- Text-to-speech
Google Gemini
The widest live language list, in the speaker’s own voice.
- 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.