SpeechSlide AI
Update
December 12, 2025

Gemini 2.5 Latest TTS Models Now Supported

Now supporting Gemini 2.5 Flash Preview TTS and Gemini 2.5 Pro Preview TTS for more diverse and high-quality voice generation.

We have added Google's latest text-to-speech models "Gemini 2.5 Flash Preview TTS" and "Gemini 2.5 Pro Preview TTS" to SpeechSlide AI.

In addition to OpenAI TTS, you can now use Gemini's high-quality speech synthesis engine, enabling more diverse voice expressions and narration generation that meets various needs.

Added Models:
・Gemini 2.5 Flash Preview TTS - Fast and lightweight voice generation
・Gemini 2.5 Pro Preview TTS - Higher quality and more expressive voice generation

You can select the new Gemini models from the voice settings. They are also a great fit for education and e-learning videos, where clear and pleasant narration matters. Please give them a try.

Update

GPT-6.1 Sol Script Generation and Four New Voice Models Are Now Available

Script generation now uses GPT-6.1 Sol, and voice settings include ElevenLabs v4 Turbo/v4 and Gemini 3.8 Flash-Lite/Flash. New slides default to Gemini Leda.

October 3, 2026
Update

OpenAI GPT-5.5 Support Released

Speech script generation now supports GPT-5.5 for higher-quality speaker notes.

June 3, 2026
Update

ElevenLabs Voice Generation Models Now Supported

SpeechSlide AI now supports ElevenLabs voice generation models, enabling more natural and expressive narration.

April 30, 2026