Vision, audio and multimodalText-to-speech1 story. An explainer is being written.Text-to-speech in the news24 Sept 2026·Google DeepMindGoogle DeepMind launches Gemini 3.8 Flash TTS voice modelsThe two new text-to-speech models let developers design custom voices from prompts and direct dialogue line by line.Related topicsMultimodal modelsVision-language modelsImage generationVideo generationSpeech recognition