Update
April 30, 2026

ElevenLabs Voice Generation Models Now Supported

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

We have added support for ElevenLabs voice generation models to SpeechSlide AI.

In addition to OpenAI TTS, Google TTS, and Gemini TTS, you can now choose ElevenLabs for natural and expressive voice synthesis.

You can select ElevenLabs from per-slide voice settings or from the global settings when generating audio for all slides. Please try it when you want narration with more natural intonation and human-like expression. It is also recommended for videos where clear narration matters, such as explanatory videos in the healthcare field.

We will continue to expand the range of available voice models to meet a wider variety of expression needs.

Update

OpenAI GPT-5.5 Support Released

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

June 3, 2026
Update

OpenAI GPT-5.4 and gpt-5.4-mini Support Released

Now supporting OpenAI GPT-5.4 and gpt-5.4-mini for higher-quality speech script generation.

April 7, 2026
Update

OpenAI GPT-5.2, GPT-5.1 Support Released

Now supporting OpenAI GPT-5.2, GPT-5.1 for more high-quality speech script generation.

February 10, 2026