With Voice Engine, OpenAI is entering the market for text-to-voice solutions based on AI.
OpenAI doesn’t stop anymore. After generating text, images and videos, the company specializing in artificial intelligence announces that it has created a model capable of generating and even imitating voices.
A text-to-voice tool
The platform, called Voice Engine, requires a text prompt and an audio sample of just 15 seconds to generate a natural voice that closely matches that of the original speaker. OpenAI promises that its tool is capable of creating “ moving and realistic voices “.
The company indicates that it began development of Voice Engine at the end of 2022. It specifies that the model already powers the predefined voices available in its speech synthesis API as well as ChatGPT Voice and Read Aloud.
As with the Sora video generator, OpenAI is cautious about the deployment of Voice Engine, “ due to the potential for misuse of synthetic voice “. The functionality is therefore not currently available to the general public.
For translation and reading assistance
The company is currently not sure whether it will eventually launch a version accessible to all, whether free or paid. “ Based on the conversations and results of small-scale testing, we will make a more informed decision about whether and how to deploy this technology on a large scale. », Communicates OpenAI.
Among applications leveraging Voice Engine, OpenAI cites the ability to provide reading assistance to non-readers and children. The service’s ability to generate natural, emotionally charged voices came in handy for education technology company Age of Learning, which used Voice Engine to generate pre-scripted voiceover content.
Another important aspect could be the translation of content, including videos and podcasts, allowing businesses and creators to reach a multilingual audience. OpenAI specifies that Voice Engine preserves the native accent of the original speaker when used for translation. Generating an English voice from the audio sample of a French speaker produces, for example, an English voice with a French accent.
Download
- Chat in different languages, including French
- Generate, translate and obtain a text summary
- Generate, optimize and correct code
Created by OpenAI, ChatGPT is an advanced chatbot powered by the latest generation GPT-4 language model. By leveraging deep learning and artificial intelligence technologies, this chatbot has the ability to decipher and understand user requests. Thanks to its ability to generate text in an ingenious way, ChatGPT offers tailored and relevant responses, ensuring smooth chat interaction and an optimized user experience.
Created by OpenAI, ChatGPT is an advanced chatbot powered by the latest generation GPT-4 language model. By leveraging deep learning and artificial intelligence technologies, this chatbot has the ability to decipher and understand user requests. Thanks to its ability to generate text in an ingenious way, ChatGPT offers tailored and relevant responses, ensuring smooth chat interaction and an optimized user experience.
Source : OpenAI
1