Home · Technology · Sep 2 archive
Meta Launches Muse Voice Transcribe with Support for 5 Indian Languages
Developing
In Short: Meta has introduced Muse Voice Transcribe, a speech-to-text model supporting 70 languages, including five Indian languages, for real-time transcription and extended audio handling.
Meta has expanded its speech-to-text capabilities with the launch of Muse Voice Transcribe, a model that supports over 70 languages, including five major Indian languages. This new technology can transcribe conversations in real-time, manage large group recordings, and handle extended audio files without additional processing.
The API is competitively priced, with a cost of $3 per 1,000 audio minutes. Meta has also shared more technical insights about the model through a research blog.
Meta has introduced Muse Voice Transcribe, a speech-to-text model supporting 70 languages, including five Indian languages, for real-time transcription and extended audio handling.
What's confirmed
What's still developing
- Tech giant Meta on Tuesday, September 1, announced a new speech-to-text model that can transcribe conversations as they happen.
- Meta said that the model supports over 70 languages, including five major Indian languages like Hindi, Tamil, Telugu, Malayalam, and Kannada.
- It is also capable of separating speakers in recordings involving more than 20 voices, and can handle recordings longer than an hour, according to Meta.
- Meta said that these capabilities are managed by a single model without a separate post-processing step.
- Meta said the model is already being used for dictation in Meta AI for Mac and Muse Code.
- The API is priced at $3 per 1,000 audio minutes, which, according to Meta, is equivalent to about $0.18 per hour.
- Meta has also published additional technical information about Muse Voice Transcribe in a research blog accompanying the launch.
Sources
- The Indian Expresslink