OpenAI, the team behind the widely popular ChatGPT language model, has introduced a new artificial intelligence called Whisper API that converts voice to text. This announcement comes after the company’s recent partnership with Microsoft to turn its successful language model GPT-3 into a source of revenue.
The Whisper API was first introduced back in September 2022, along with ChatGPT, and ever since then, it has been refined to produce accurate voice-to-text conversion. In order to use the Whisper API, users will have to upload an audio recording to the program, which is then converted into text in a short time. As of now, we understand that the API supports various formats such as M4A, MP3, MP4, MPEG, MPGA, WAV, and WEBM as input, and it is said to achieve high accuracy even with different accents, thanks to its 680,000-hour multilingual training library.
According to the company, Whisper API supports other languages too along with English, and it is definitely a significant advantage. The service can convert speech to text in multiple languages, making it a valuable tool for businesses and individuals working with multilingual content.
OpenAI’s Whisper API has been trained on a diverse range of data that includes thousands of hours of speech from various sources, such as movies, audiobooks, and news broadcasts. This training has resulted in the model achieving high accuracy in speech-to-text conversion, even with different accents and background noise.
The Whisper API is a versatile tool that can be used for several applications, including transcribing interviews, podcasts, and conference calls. We can also see its future potential in real-time transcription for live events and meetings, automatic subtitling for videos, and voice-activated assistants for individuals with speech impairments. The model’s ability to support multiple languages makes it an essential tool for businesses and individuals working with multilingual content.
As OpenAI continues to refine the Whisper API, we can expect even more advanced accuracy and functionality in the future. The Whisper API is now available for use, and interested parties can access it by clicking the link provided by OpenAI. With the rise of voice search and voice-activated technology, the Whisper API offers a practical solution for converting speech to text accurately and quickly. OpenAI continues to innovate with its artificial intelligence, and the Whisper API looks like another step in this direction.