Jakarta (MidLand) – Artificial intelligence and natural language processing product development company Prosa.ai presents a product Speech synthesis (TTS), a cloud-based solution that can convert text to speech in Indonesian and English.
“Prosa.ai also increases its innovation by featuring other voice characters, such as the voice of Dimas (male) with a formal speaking style, Dimas with an expressive speaking style, and Ocha (female) with a friendly speaking style,” he stated Co-founder and Prosa.ai CEO Teguh Eko Budiarto, as quoted in the company’s press release on Saturday (4/6).
“Using the Dimas and Ocha speech pattern is best suited for reading news and voice-over,” He added.
Prosa.ai offers significant improvements to the TTS product compared to the 2021 version. In the latest product version, Prosa.ai provides 10 new voice variations, including English voices.
The product update also includes a custom pause and sound feature that allows users to create up to 40 different sound variations in a short time and download them in a variety of audio formats that support use in platforms such as YouTube videos and TikTok.
Read also: OpenAI reveals new tool capable of cloning voices
Read also: ChatGPT can now be used without an account
Based on the results of the latest survey conducted by the Prosa TTS team, usage audiobook occupies the first position with a percentage of 24% of the total audio generation.
To meet these usage needs, Prosa creates sounds specifically designed for audiobook in Indonesian whose character is called Dini.
Dini’s voice is considered very suitable for telling stories because it has a soft and thoughtful speaking style, as well as better pronunciation accuracy and prosody.
Prose TTS comes with various features to make it easier for users like Speech synthesizer to also make the conversion of written text into speech easier Human sounding voices which allows users to choose natural human voice characteristics and speaking styles.
Furthermore, there are features Voice tuning to adjust the pitch and tone and also adjust the speaking speed Flexible audio file which can output audio in various formats (WAV, MP3 and OPUS) so that users can play and save audio.
“Another characteristic we want to develop is the emotional characteristic of the sound, and we want to develop that market For vocal talent who want to be part of the Prose TTS voice and benefit from it market this, Teguh said.
In addition to TTS, Prosa.ai provides other products to meet business needs such as speech to text conversion.
Read also: Kaskus announces an investment in Prosa.ai
Read also: Brave launches AI assistant on iPhone and iPad
Reporter: Vinny Shoffa Salma
Publisher: Maryati
Copyright © MidLand 2024
Quoted From Many Source
