Skip to Content
Artificial intelligence

Google’s AI can now translate your speech while keeping your voice

Researchers trained a neural network to map audio “voiceprints” from one language to another.
May 20, 2019
An image of U.N. Secretary-General Ban Ki-moon listening to a translation device
An image of U.N. Secretary-General Ban Ki-moon listening to a translation deviceEMILIO MORENATTI/AP

Listen to this Spanish audio clip.

This is how its English translation might sound when put through a traditional automated translation system.

Now this is how it sounds when put through Google’s new automated translation system.

The results aren’t perfect, but you can sort of hear how Google’s translator was able to retain the voice and tone of the original speaker. It can do this because it converts audio input directly to audio output without any intermediary steps. In contrast, traditional translational systems convert audio into text, translate the text, and then resynthesize the audio, losing the characteristics of the original voice along the way.

The new system, dubbed the Translatotron, has three components, all of which look at the speaker’s audio spectrogram—a visual snapshot of the frequencies used when the sound is playing, often called a voiceprint.  The first component uses a neural network trained to map the audio spectrogram in the input language to the audio spectrogram in the output language. The second converts the spectrogram into an audio wave that can be played. The third component can then layer the original speaker’s vocal characteristics back into the final audio output.

Not only does this approach produce more nuanced translations by retaining important nonverbal cues, but in theory it should also minimize translation error, because it reduces the task to fewer steps.

Translatotron is currently a proof of concept. During testing, the researchers trialed the system only with Spanish-to-English translation, which already took a lot of carefully curated training data. But audio outputs like the clip above demonstrate the potential for a commercial system later down the line. You can listen to more of them here.

Deep Dive

Artificial intelligence

How to opt out of Meta’s AI training

Your posts are a gold mine, especially as companies start to run out of AI training data.

Apple is promising personalized AI in a private cloud. Here’s how that will work.

Apple’s first big salvo in the AI wars makes a bet that people will care about data privacy when automating tasks.

This AI-powered “black box” could make surgery safer

A new smart monitoring system could help doctors avoid mistakes—but it’s also alarming some surgeons and leading to sabotage.

An AI startup made a hyperrealistic deepfake of me that’s so good it’s scary

Synthesia's new technology is impressive but raises big questions about a world where we increasingly can’t tell what’s real.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.