Skip to content

Conversation

@Nsuccess
Copy link
Contributor

Description

This PR adds a new TTS extension for NVIDIA Riva Speech Skills, providing high-quality GPU-accelerated text-to-speech synthesis.

Features

  • Streaming synthesis using NVIDIA Riva gRPC API
  • Support for multiple languages and voices
  • Configurable sample rates and SSL options
  • Comprehensive error handling and logging
  • TTFB metrics support

Testing

  • 30+ test cases covering configuration, extension lifecycle, and API compliance
  • Follows TTS2 interface pattern used by other TTS extensions
  • Compatible with existing TEN Framework infrastructure

Documentation

  • Complete README with setup instructions
  • Technical implementation details
  • Configuration examples
  • NVIDIA Riva server setup guide

Closes #1964

- Implements text-to-speech using NVIDIA Riva Speech Skills
- Supports streaming synthesis with gRPC
- Includes comprehensive tests and documentation
- Follows TTS2 interface pattern

Closes TEN-framework#1964
@plutoless plutoless merged commit 21d2717 into TEN-framework:main Jan 20, 2026
11 of 27 checks passed
@plutoless
Copy link
Contributor

thank you for the PR!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[2026NewYearChallenge 🏅] Create a NVIDIA Riva TTS Extension

2 participants