Breaking news: Acapela’s neural digital voices, based on VoiceAI, are ready to speech empower services and applications here and now with Acapela Cloud.

Real time neural TTS by Acapela.


“We are very pleased to announce a big step forward and to disclose that our neural TTS voices are NOW available in real time, which makes a big difference on the voice market offer” says Rémy Cadic, CEO of Acapela Group.

Based on our latest in-house innovation, Acapela’s highest quality voice portfolio allows for the generation of realistic, lifelike audio output, setting up a new standard for real-time natural interactions and an advanced user experience.

Major step forward

The full customer journey immediately benefits from this major enhancement, and notably for voice bot and call bot experiences. Lower latency will offer an improved voice animation for your content, especially in contexts such as e-learning, with unequalled TTS audio quality.
The SSML* support will ease the full process to ensure a smooth switch to real time neural voices from Acapela and offers a seamless transition of audio tag usage.

Acapela’s neural TTS voices are available in streaming mode via our Acapela Cloud online service. Take advantage of it and get a head start in making the most of those very high-quality voices.

To access Acapela Group’s neural TTS voices in preview, please contact us.

The quality of Acapela Group’s neural digital voices relies on an invaluable asset which makes all the difference: vocal databases rich with 20 years of voice portfolio development. We are talking about a new technology, capable of overcoming the limits of the quality reached with unit selection text to speech, the technology that is widely used today.
“Besides the Standard and Premium portfolios, Neural TTS technology strengthens voice marketing strategies by designing custom voices that will enhance brand identity, offer outstanding conversational user experience, and increase customer satisfaction and confidence. We look forward to accompanying our customers and partners in this new technology milestone”, adds Remy Cadic, CEO of Acapela Group.


* SSML (Speech Synthesis Markup Language) is an XML-based markup language that lets developers specify how input text is converted into synthesized speech by using text-to-speech.