# Speech-to-speech

> Realtime models that take audio in and give audio out, in one service.

Source: https://polvallverdu.github.io/pipedog/docs/services/s2s/



{/* Generated by scripts/generate-providers.ts from data/providers.ts. */}

A speech-to-speech service replaces the STT, LLM and TTS trio with one realtime model: audio in, audio and text out, with function calls.

| Provider                                                          | Classes                      | Package             | Status |
| ----------------------------------------------------------------- | ---------------------------- | ------------------- | ------ |
| [OpenAI Realtime](https://polvallverdu.github.io/pipedog/docs/services/s2s/openai.md)                      | `OpenAIRealtimeLLMService`   | `@pipedog/openai`   | Ported |
| [OpenAI Live](https://polvallverdu.github.io/pipedog/docs/services/s2s/openai-live.md)                     | `OpenAILiveLLMService`       | `@pipedog/openai`   | Ported |
| [Gemini Live](https://polvallverdu.github.io/pipedog/docs/services/s2s/gemini-live.md)                     | `GeminiLiveLLMService`       | `@pipedog/google`   | Ported |
| [Gemini Live on Vertex AI](https://polvallverdu.github.io/pipedog/docs/services/s2s/gemini-live-vertex.md) | `GeminiLiveVertexLLMService` | `@pipedog/google`   | Ported |
| [Inworld Realtime](https://polvallverdu.github.io/pipedog/docs/services/s2s/inworld.md)                    | `InworldRealtimeLLMService`  | `@pipedog/inworld`  | Ported |
| [Ultravox](https://polvallverdu.github.io/pipedog/docs/services/s2s/ultravox.md)                           | `UltravoxRealtimeLLMService` | `@pipedog/ultravox` | Ported |
| [xAI Grok Realtime](https://polvallverdu.github.io/pipedog/docs/services/s2s/grok.md)                      | `GrokRealtimeLLMService`     | `@pipedog/xai`      | Ported |
| [AWS Nova Sonic](https://polvallverdu.github.io/pipedog/docs/services/s2s/aws.md)                          | `AWSNovaSonicLLMService`     | `@pipedog/aws`      | Ported |
| [Azure Voice Live](https://polvallverdu.github.io/pipedog/docs/services/s2s/azure-voice-live.md)           | `AzureVoiceLiveLLMService`   | `@pipedog/azure`    | Ported |
| [Azure OpenAI Realtime](https://polvallverdu.github.io/pipedog/docs/services/s2s/azure-realtime.md)        | `AzureRealtimeLLMService`    | `@pipedog/azure`    | Ported |

Pipecat's [speech-to-speech reference](https://docs.pipecat.ai/api-reference/server/services/s2s) lists every upstream provider. Those not in this table are on [Other upstream providers](https://polvallverdu.github.io/pipedog/docs/services/other-upstream.md).