Text to Speech
The Text to Speech interface converts written text into natural, human-like speech, tuned for Indian accents and dialects. It draws from the same Voice Library used across Sarvam Creative, so the persona you pick here is the same one you can reuse in Dubbing - a project’s “voice” stays consistent across every asset you generate for it.
Popular Use Cases
- Narration for e-learning modules and explainer videos.
- Voiceovers for ads, promos, and social content.
- IVR prompts and in-app voice notifications.
- Audiobook and long-form narration.
Key Facts
Credit cost is calculated from the character count of your input text, and is estimated live as you type - for example, the screen shows “327 characters · ~0.98 credits” for a sample paragraph.
You can synthesize using either curated Sarvam voices or any voice you’ve created yourself in Voice Cloning - both appear as tabs in the same panel. If you have no cloned voices yet, that tab shows a Clone a voice button that takes you straight into the cloning flow without leaving Text to Speech.