> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# Speech

## Docs

- [Voice Pipelines](https://docs.nvidia.com/dynamo/dev/speech/voice-pipelines.md): Serve speech recognition, LLM, and text-to-speech stages for voice agents
- [Speech to Text (STT)](https://docs.nvidia.com/dynamo/dev/speech/speech-to-text.md): Stream audio to a speech recognition model and receive transcripts over the /v1/realtime WebSocket
- [Text-to-Speech](https://docs.nvidia.com/dynamo/dev/speech/text-to-speech.md): Synthesize speech with vLLM-Omni through the /v1/audio/speech endpoint
- [Speech-to-Speech](https://docs.nvidia.com/dynamo/dev/speech/speech-to-speech.md): Stream audio to a vLLM-Omni model and receive spoken responses over /v1/realtime