Next Step in Speech Synthesis
On September 23, 2026, Google DeepMind officially announced Gemini 3.8 Text-to-Speech in a brief update on its research blog. This marks the Google research lab's latest step toward broadening speech generation capabilities within the Gemini model ecosystem.
Technical Details Awaited
According to the initial announcement on the Google DeepMind Blog, the release serves as a brief introduction without in-depth technical specifications. Key details—including model architecture, supported languages, audio sample fidelity, API availability, and pricing—have not yet been disclosed in this release.