Batch TTS

Text to Speech — Batch

Convert text to audio via HTTP POST. Receive a complete audio file in a single response.

How it works

Batch synthesis sends text to POST /v1/audio/speech and waits for the complete audio result.

PropertyValue
TransportHTTP POST
Endpointhttps://tts.shunyalabs.ai/v1/audio/speech
AuthAuthorization: Bearer <API_KEY>
Required fieldsmodel, voice, input
Default formatmp3

When to use batch

  • Pre-rendered voice prompts for IVR and telephony systems
  • Notification audio — order updates, alerts, reminders
  • Podcast, audiobook, and long-form content generation
  • Any use case where real-time latency is not critical
Start here

Your First Request →

End-to-end walkthrough from install to audio output.

Reference

TTSConfig Parameters →

Every TTSConfig parameter in one table.

PreviousAuthentication & API KeysNext Your First Request