Skip to main content

Documentation

Build with Somya’s voice APIs

Everything you need to add speech to your product: guides, model documentation, and a full API reference for real-time text-to-speech, speech-to-text, and voice cloning.

Open the docs

Quickstart

Make your first text-to-speech and speech-to-text calls in minutes. Set up authentication, send a request, and play back your first generated audio.

Read the quickstart

Models

Learn what Panini (text-to-speech) and Vyasa (speech-to-text) can do: supported languages, voices, streaming modes, audio formats, and best practices for production workloads.

Explore the models

API reference

Complete endpoint documentation generated from our OpenAPI spec — request and response schemas, streaming protocols, error codes, and rate limits.

Browse the API reference