Models by Alibaba Cloud
Qwen in Tõlk: bilingual captions, every speaker labelled.
Qwen3.8 LiveTranslate translates speech to speech and returns captions in both languages, with speaker diarization built in. It is opt-in for accounts that allow processing outside the EEA.
- Speech-to-speech
Models and how they run.
- Speech-to-speech
Qwen3.8 LiveTranslate Flash
qwen3.8-livetranslate-flash-realtime
One live session per language over Model Studio realtime.
Why teams pick it
- Source and target captions from one session
- Realtime speaker diarization
- About 2.3 s average lag
- Dictionary terms passed as hotwords
Good to know
- Enabled per account by the account holder; processed in Singapore.
- Switch it off any time and those languages move to OpenAI or Gemini at once.
Languages
Major world languages, captioned both ways
A curated list of world languages, each with one clear voice and bilingual captions.
Languages listeners can hear the translation in.
Qwen3.8 LiveTranslateSpeech-to-speech29 languages
- Arabic
- Chinese
- Czech
- Danish
- Dutch
- English
- Filipino
- Finnish
- French
- German
- Hebrew
- Hindi
- Icelandic
- Indonesian
- Italian
- Japanese
- Korean
- Malay
- Norwegian (Bokmål)
- Persian
- Polish
- Portuguese
- Russian
- Spanish
- Swedish
- Thai
- Turkish
- Urdu
- Vietnamese
Tõlk shows which engines can serve each language when you set up an event.
Where Qwen works best.
No setup on your side
Qwen 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.
Qwen is a trademark of Alibaba Cloud. Tõlk uses its models through Alibaba Cloud’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
Google Gemini
The widest live language list, in the speaker’s own voice.
- Speech-to-speech
- Speech-to-text
- Text translation
- Text-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.