Creating long form TTS audio on AI studio

Viggo_paul · October 18, 2025, 9:47pm

I need help/recommendation on which model or method to use to enable me create longer Voice overs (40 - 60 minutes) for my YouTube videos.

Shivam_Singh2 · October 31, 2025, 10:44am

Hi @Viggo_paul
Welcome to the AI Forum!!!

For creating 40–60 minute voice-overs, I recommend you to use Google Cloud Text-to-Speech Long Audio Synthesis. It supports long-form text asynchronously and outputs audio to a Google Cloud Storage bucket.
You can find more details here Google Cloud Long Audio TTS docs.

Topic		Replies	Views
Using the narrators voice General Discussion help_request	4	483	July 12, 2021
How do I build a custom voice recognition model for multiple people? TF.js tfjs , datasets , help_request	24	7181	September 18, 2021
Implementing a CNN LSTM architecture for audio segmentation TensorFlow models , keras , help_request	16	3405	July 1, 2021
Transcribe text to text and vice versa, speech to speech and image to text in a flutter app using gemini Gemini API	15	732	May 20, 2024
What is the limit on audio length when using Gemini API to do ASR task? Gemini API	1	223	July 2, 2024

Creating long form TTS audio on AI studio

Related topics