Deepdub Launches Phantom Z 3.4 Conversational Voice Model

Sep 3, 2026
Deepdub has released a multilingual text to speech model with 48 kHz audio, support for more than 50 locales, and a 150 millisecond response time.

Deepdub announced in a press release the launch of Phantom Z 3.4 Conversational, a multilingual text to speech model available to all its clients. It produces 48 kHz audio and supports more than 50 locales and dialects.

The model has a p95 time to first audio of 150 milliseconds in real time mode. It can transfer a voice across languages using less than three seconds of reference audio. Its text normalization handles content such as account numbers, dates, invoice totals, and appointment times.

Phantom Z 3.4 Conversational also expands support for Hebrew. It uses sentence context to select pronunciations, supports custom pronunciation markings, and converts national ID numbers, dates, and transaction amounts into spoken forms.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Industry analysis

2025 Global Business Services Agenda: Gen AI Takes Center Stage

The Hackett Group

This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.