Generate text-to-speech with Google AI Studio Gemini 2.5 | Alpha | PandaiTech

Generate text-to-speech with Google AI Studio Gemini 2.5

How to access and use the Gemini 2.5 model in Google AI Studio to generate expressive text-to-speech audio, including selecting voices and adjusting emotional tone.

Learning Timeline
Key Insights

Multilingual Limitations

While the model can attempt multiple languages, current performance shows noticeable errors and pronunciation issues. For best results, stick to the primary supported language or carefully audit non-English outputs.
Prompts

Example Prompt: Angry Tone

Target: Google AI Studio TTS
I can't believe you do this to me, you absolute traitor.

Example Prompt: Sad Tone

Target: Google AI Studio TTS
I never thought I would have to say goodbye so soon. And now that you're gone, every moment feels like an endless ache in my heart.
Step by Step

Generating Expressive Text-to-Speech in Google AI Studio

  1. Navigate to the main interface of Google AI Studio.
  2. Locate the 'Text-to-Speech' button, typically found at the bottom of the sidebar or tool menu.
  3. Click the button to open the Text-to-Speech configuration panel.
  4. Select the desired mode: 'Single speaker' or 'Multi-speaker'.
  5. Choose a specific voice profile from the available list of default voices.
  6. Type or paste the desired text into the main input field.
  7. Adjust the emotional tone setting (e.g., change from 'Neutral' to 'Sad' or 'Angry') using the configuration options located above the text input.
  8. Click the generate or play button to synthesize the audio and review the output.

More from Create AI Voice & Music

View All