Original post
Chubby♨️#1532
Chubby♨️#1532
Say hello, hola, 你好 to Gemini 3.5 Live Translate: our latest audio model built for fast, cross-language communication. 🌐
8:18 AM · Jun 9, 2026 · 108.6K Views
Google launches Gemini 3.5 Live Translate, a streaming speech-to-speech model supporting over 70 languages
AI Judge changed title after evaluation, original title: "Google launches Gemini 3.5 Flash Live Translate for real-time, low-latency speech-to-speech translation in 70 languages"
Story Overview
Google is shipping a specialized audio model that turns spoken words into natural-sounding speech in another language on the fly, handling more than 70 tongues and over 2,000 language pairs while staying synced with the original speaker even when background noise gets loud.
4956.7K6451.6K664.2K
Developer Impact
Access starts today via API and AI Studio
Developers can try the model immediately through the Gemini API and Google AI Studio, while regular users already see it inside the Google Translate app; exact pricing tiers remain listed only as preview placeholders for now.
Open Question
Meet integration still on the horizon
The feature is expected in Google Meet soon, yet no firm date has been shared, leaving the timeline for full video-call rollout as the clearest open detail.
Sentiment
People praise Gemini 3.5 Live Translate for its natural real-time speech-to-speech translation in many languages, likening it to magic or a Star Trek breakthrough, while others criticize the lack of dialects like Spain Spanish.
Pos
70.0%
Neg
30.0%
141 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS400.5KBOOKMARKS1KLIKES3.8KRETWEETS329REPLIES191
Logan Kilpatrick@OfficialLoganK
Introducing Gemini 3.5 Flash Live Translate, our real time speech to speech translation model which supports more than 70 languages (both in and out), and is so natural.
It is available in the Gemini API, AI Studio, & Google Translate right now + coming soon to Google Meet!!
1dViews 400.5KLikes 3.8KBookmarks 1K
Google AI Studio@GoogleAIStudio
http://x.com/i/article/2064376197250007040
1dViews 70KLikes 994Bookmarks 237
Philipp Schmid@_philschmid
Gemini 3.5 Live Translate! We just shipped a real-time babel fish.
- 70+ languages, 2,000+ language pairs. - Natural translated speech, works in noisy environments. - Stays in sync with the speaker, no lag, no awkward pauses. - Auto-detects the language being spoken.
Available today in Google Translate (Android & iOS), the Gemini API (Public Preview), and Google Meet (Private Preview).
I genuinely think this is the beginning of the end of language barriers. Anyone can now speak and understand anyone.
1dViews 16.2KLikes 300Bookmarks 98
Jeff Dean@JeffDean
Speech translation has been one of the longest-running ML efforts at Google, and we’ve come a long way. Gemini 3.5 Live Translate is our latest speech-to-speech model, supporting 70+ languages. It enables more natural conversations across languages in everyday products and apps.
Here’s an example of how partners at @InsideGrab are helping connect travelers with drivers. 🚗
Rolling out in Google Translate and via the Live API in @GoogleAIStudio.
1dViews 28.6KLikes 343Bookmarks 71
Rohan Paul@rohanpaul_ai
Fascinating. Google just released Gemini 3.5 Live Translate.
A live speech-to-speech translation model that starts speaking in another language while the original speaker is still talking.
Older translation systems often wait for a full sentence, because early words can be misleading until later words reveal tense, intent, or context.
Gemini 3.5 instead runs streaming translation, where the model listens, interprets partial meaning, predicts what can safely be translated, and keeps updating as new speech arrives.
supports 70+ languages, stays only a few seconds behind the speaker, and can preserve pacing, pitch, and intonation across longer sessions.
Rolling out to Gemini Live API, businesses through Google Meet preview, and regular users through Google Translate on Android and iOS.
Google AI@GoogleAI
Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation.
It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy audio, just real connection without language barriers.
So, how does it work? 🤔
The model is able to make split-second decisions to juggle speed and translation quality so conversations actually feel fluid, human, and natural. In order to do this, the model must receive and contextualize the input while simultaneously outputting the translated speech.
Through this process, Gemini 3.5 Live Translate manages to stay mere seconds behind each speaker and can even maintain pacing, pitch, and intonation across extended sessions.
See it in action below, or try it yourself in the Google Translate app on iOS & Android.
1dViews 11.5KLikes 93Bookmarks 40
Logan Kilpatrick@OfficialLoganK
sorry not Flash ** Just Gemini 3.5 Live Translate : )
Logan Kilpatrick@OfficialLoganK
Introducing Gemini 3.5 Flash Live Translate, our real time speech to speech translation model which supports more than 70 languages (both in and out), and is so natural.
It is available in the Gemini API, AI Studio, & Google Translate right now + coming soon to Google Meet!!
1dViews 15.5KLikes 145Bookmarks 5
Google DeepMind@GoogleDeepMind
3.5 Live Translate can convert speech into over 70 languages and processes it as it’s streamed - while keeping tone, pace and pitch intact - allowing for more natural conversations.
1dViews 5.9KLikes 61Bookmarks 11
👩💻 Paige Bailey@DynamicWebPaige
🐟 Hitchhikers Guide fans, rejoice!
Babelfish has been achieved internally:
Logan Kilpatrick@OfficialLoganK
Introducing Gemini 3.5 Flash Live Translate, our real time speech to speech translation model which supports more than 70 languages (both in and out), and is so natural.
It is available in the Gemini API, AI Studio, & Google Translate right now + coming soon to Google Meet!!
1dViews 8.6KLikes 63Bookmarks 10
Philipp Schmid@_philschmid
Docs: http://ai.google.dev/gemini-api/docs/live-api/live-translate GitHub: http://github.com/google-gemini/gemini-live-api-examples Blog: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-live-3-5-translate/
Philipp Schmid@_philschmid
Gemini 3.5 Live Translate! We just shipped a real-time babel fish.
- 70+ languages, 2,000+ language pairs. - Natural translated speech, works in noisy environments. - Stays in sync with the speaker, no lag, no awkward pauses. - Auto-detects the language being spoken.
Available today in Google Translate (Android & iOS), the Gemini API (Public Preview), and Google Meet (Private Preview).
I genuinely think this is the beginning of the end of language barriers. Anyone can now speak and understand anyone.
1dViews 1.5KLikes 14Bookmarks 8
Jeff Dean@JeffDean
You can read more about this here: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-live-3-5-translate/
Jeff Dean@JeffDean
Speech translation has been one of the longest-running ML efforts at Google, and we’ve come a long way. Gemini 3.5 Live Translate is our latest speech-to-speech model, supporting 70+ languages. It enables more natural conversations across languages in everyday products and apps.
Here’s an example of how partners at @InsideGrab are helping connect travelers with drivers. 🚗
Rolling out in Google Translate and via the Live API in @GoogleAIStudio.
1dViews 6.2KLikes 23Bookmarks 6
Google DeepMind@GoogleDeepMind
Try it in the @Google Translate app or build in preview via the API in @GoogleAIStudio. Find out more ↓ https://goo.gle/4aEtspk
1dViews 4.9KLikes 15Bookmarks 2
Rohan Paul@rohanpaul_ai
API docs for Live translation with Gemini Live API
https://ai.google.dev/gemini-api/docs/live-api/live-translate
Rohan Paul@rohanpaul_ai
Fascinating. Google just released Gemini 3.5 Live Translate.
A live speech-to-speech translation model that starts speaking in another language while the original speaker is still talking.
Older translation systems often wait for a full sentence, because early words can be misleading until later words reveal tense, intent, or context.
Gemini 3.5 instead runs streaming translation, where the model listens, interprets partial meaning, predicts what can safely be translated, and keeps updating as new speech arrives.
supports 70+ languages, stays only a few seconds behind the speaker, and can preserve pacing, pitch, and intonation across longer sessions.
Rolling out to Gemini Live API, businesses through Google Meet preview, and regular users through Google Translate on Android and iOS.
1dViews 1.8KLikes 3Bookmarks 1
swyx@swyx
@OfficialLoganK looking good @thorwebdev !
Logan Kilpatrick@OfficialLoganK
Introducing Gemini 3.5 Flash Live Translate, our real time speech to speech translation model which supports more than 70 languages (both in and out), and is so natural.
It is available in the Gemini API, AI Studio, & Google Translate right now + coming soon to Google Meet!!
1dViews 1.2KLikes 8Bookmarks 1
Nataniel Ruiz@natanielruizg
this is the tweet
👩💻 Paige Bailey@DynamicWebPaige
🐟 Hitchhikers Guide fans, rejoice!
Babelfish has been achieved internally:
17hViews 3.8KLikes 5Bookmarks 1
swyx@swyx
@OfficialLoganK @GoogleAIStudio
Logan Kilpatrick@OfficialLoganK
@GoogleAIStudio you can read the API docs here, very excited to see this land and drive more multi-lingual experiences: https://ai.google.dev/gemini-api/docs/live-api/live-translate
1dViews 3.2KLikes 3Bookmarks 0
Tharindu Indrajith@tikzoxs
@OfficialLoganK @GeminiApp @GoogleAIStudio we need Gemini 3.5 flash live speech to text API. Coz the Google Speech to text does not work well for strong accents. Gemini works extremely well with context and Google speech to text only works with local context.
1dViews 284Likes 1Bookmarks 1
Ferbin@Ferbin08
@OfficialLoganK Latency is everything in real-time translation. Sub-200ms feels natural, above that conversations get awkward. 70 languages is impressive. But are all 70 hitting that latency target or is it tiered?
1dViews 110Likes 1
Olga Alexandrova@OlgaAle41223914
@GoogleDeepMind "cross-language communication" fast is the part that gets me. tried live translate on gemini vs piping audio through gpt and the lag difference was night and day, gemini barely paused between languages.
1dViews 182Bookmarks 1
WK@zoom_will
@OfficialLoganK Bro, when Gemini 3.5 pro? Even beta, it’s already June
1dViews 108Likes 4
Angel 🌼@Angaisb_
@_philschmid No Spanish from Spain, just latin american Spanish
I liked Google because you usually included it, it's a shame you didn't this time because the model does seem to be good
1dViews 192Likes 3
Load more posts