Set the scene with Gemini TTS

<p>Roll tape and prompt! In this episode of Two Voice Devs, Allen and Mark explore how Google’s new advanced prompting guidelines turn developers into voice directors for Gemini Text-to-Speech. Instead of coding rigid SSML tags, you can now establish a scene, write stage directions, and give &quot;director&#39;s notes&quot; to shape a base voice&#39;s gender, accent, style, and pacing.</p><p><br></p><p>Allen showcases a web app where he directs a single base voice—to play two entirely different characters: a rough Brooklyn cab driver and a classic Southern belle. The hosts discuss using natural language audio tags as cues for laughter, sighs, gasps, and more, and how these theatrical controls are coming alive in real-time with Gemini Live and Gemini 3.1 Flash TTS.</p><p><br></p><p>Learn more:</p><p>* https://ai.google.dev/gemini-api/docs/speech-generation</p><p><br></p><p>[00:00:05] Welcome to Two Voice Devs</p><p>[00:00:27] Intro to Gemini Text-to-Speech and Advanced Prompting</p><p>[00:01:57] Moving Beyond SSML to Flexible Base Voices</p><p>[00:03:07] Prompting Genders and Accents (The Storytelling Analogy)</p><p>[00:04:40] Web App Demo: Zephyr as a Brooklyn Cab Driver vs. Southern Belle</p><p>[00:06:50] Building Multi-Voice Conversations with Stage Directions</p><p>[00:08:41] Using Natural Language Audio Tags for Expressive Cues</p><p>[00:11:02] Gemini Live Integration and Dynamic Tone Selection</p><p>[00:12:27] Model Details: Gemini 3.1 Flash TTS Preview and Release Info</p><p>[00:13:53] Wrap-up and Call for Feedback</p><p><br></p><p>Hashtags:</p><p>#GeminiTTS #TextToSpeech #GenerativeAI #GoogleDeepMind #GeminiLive #GeminiFlash #AIStudio #DeveloperTools #SpeechSynthesis #VoiceFirst #AdvancedPrompting</p><p><br></p><p>Episode 275</p>