Voicebox by Meta icon

Voicebox by Meta

No ratings
Versatile audio output via speech generation.
Generated by ChatGPT

Voicebox is a generative AI model for speech that can generalize to tasks it was not specifically trained for with state-of-the-art performance. Unlike existing speech synthesizers, it can be trained on diverse, unstructured data without requiring carefully labeled inputs.

Voicebox uses a new approach called Flow Matching, which is a Meta's latest advancement on non-autoregressive generative models that can learn highly non-deterministic mapping between text and speech.

Voicebox can produce high-quality audio clips in a vast variety of styles and can synthesize speech across six languages, as well as perform noise removal, content editing, style conversion, and diverse sample generation.

One of the main advantages of Voicebox is its ability to modify any part of a given sample, not just the end of an audio clip it is given. This makes it highly versatile and suitable for tasks such as in-context text-to-speech synthesis, cross-lingual style transfer, speech denoising and editing, and diverse speech sampling.

Additionally, Voicebox outperforms existing state-of-the-art speech models on word error rate and audio similarity metrics. While Voicebox is not currently available to the public due to potential risks of misuse, Meta has shared audio samples and a research paper detailing its approach and results.

This breakthrough in generative AI for speech is exciting as it has potential applications in helping people communicate and customize voices for virtual assistants.


Community ratings

No ratings yet.

How would you rate Voicebox by Meta?

Help other people by letting them know if this AI was useful.


Feature requests

Are you looking for a specific feature that's not present in Voicebox by Meta?
Voicebox by Meta was manually vetted by our editorial team and was first featured on June 16th 2023.
Promote this AI Claim this AI

Pros and Cons


Generative model
Generalizes to untrained tasks
Trains on diverse data
Doesn't require labeled inputs
Uses Flow Matching
High-quality audio clips
Operates in six languages
Performs noise removal
Performs content editing
Performs style conversion
Does diverse sample generation
Can modify any sample part
In-context text-to-speech synthesis
Performs cross-lingual style transfer
Performs speech denoising
Performs speech editing
Performs diverse speech sampling
Outperforms other models
Superior word error rate
Superior audio similarity metrics
Versatile across tasks
Significant potential applications
Style transfer capability
Audio editing functionality
Large data scale training
Trains on unstructured data
Effective model classifier
Potential virtual assistant voices
Fast performance
Effective for in-wild data
Potential for synthetic data generation
Trains on multilingual benchmarks


Not available to public
Potential for misuse
Requires a lot of data
Limited to six languages
20 times slower than Vall-E
Depends on Flow Matching
Doesn't support task-specific training
Currently lacks public API
Lacks verification functionality
No open-source code


What are the key features of Voicebox by Meta?
What does the Flow Matching approach utilized by Voicebox entail?
In what languages can Voicebox synthesize speech?
How does Voicebox perform in terms of word error rate and audio similarity metrics compared to existing models?
What makes Voicebox different from traditional speech synthesizers?
How can Voicebox modify any part of a given audio sample?
Is Voicebox available for public use?
What are the potential applications of Voicebox?
What data was Voicebox trained on?
Can Voicebox perform speech denoising and editing?
How does Voicebox handle diverse speech sampling?
Can Voicebox perform in-context text-to-speech synthesis?
Does Voicebox have the ability to perform cross-lingual style transfer?
How does Voicebox handle content editing and style conversion?
How efficient is Voicebox compared to existing models?
Can Voicebox create outputs from scratch?
What measures are being taken to avoid misuse of Voicebox?
What makes Voicebox suitable for tasks such as in-context text-to-speech synthesis, cross-lingual style transfer, speech denoising, and editing?
What is the impact of Voicebox on synthetic speech recognition?
What potential risks have been identified with Voicebox technology?

If you liked Voicebox by Meta


+ D bookmark this site for future reference
+ ↑/↓ go to top/bottom
+ ←/→ sort chronologically/alphabetically
↑↓←→ navigation
Enter open selected entry in new tab
⇧ + Enter open selected entry in new tab
⇧ + ↑/↓ expand/collapse list
/ focus search
Esc remove focus from search
A-Z go to letter (when A-Z sorting is enabled)
+ submit an entry
? toggle help menu
0 AIs selected
Clear selection