Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions docs.json
Original file line number Diff line number Diff line change
Expand Up @@ -200,6 +200,7 @@
"server/services/tts/rime",
"server/services/tts/sarvam",
"server/services/tts/speechmatics",
"server/services/tts/voiceai",
"server/services/tts/xtts"
]
},
Expand Down
1 change: 1 addition & 0 deletions server/services/supported-services.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,7 @@ Text-to-Speech services receive text input and output audio streams or chunks.
| [Rime](/server/services/tts/rime) | `pip install "pipecat-ai[rime]"` |
| [Sarvam](/server/services/tts/sarvam) | No dependencies required |
| [Speechmatics](/server/services/tts/speechmatics) | `pip install "pipecat-ai[speechmatics]"` |
| [Voice.ai](/server/services/tts/voiceai) | `pip install "pipecat-ai[voiceai]"` |
| [XTTS](/server/services/tts/xtts) | `pip install "pipecat-ai[xtts]"` |

## Speech-to-Speech
Expand Down
62 changes: 62 additions & 0 deletions server/services/tts/voiceai.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,62 @@
---
title: "Voice.ai"
description: "Text-to-speech service using Voice.ai's TTS API"
---

## Overview

Voice.ai provides high-quality text-to-speech synthesis using Voice.ai's TTS WebSocket API with ultra-low latency and support for multiple concurrent TTS streams. The service offers various voice models and languages optimized for conversational AI applications requiring low latency and automatic interruption handling.

<CardGroup cols={2}>
<Card
title="Voice.ai TTS API Reference"
icon="code"
href="https://reference-server.pipecat.ai/en/latest/api/pipecat.services.voiceai.tts.html"
>
Pipecat's API methods for Voice.ai TTS integration
</Card>
<Card
title="Example Implementation"
icon="play"
href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/07zl-interruptible-voiceai.py"
>
Complete example with Voice.ai TTS and interruption handling
</Card>
<Card
title="Voice.ai"
icon="book"
href="https://voice.ai"
>
Voice.ai platform and developer resources
</Card>
<Card
title="Voice Library"
icon="microphone"
href="https://voice.ai/app/dashboard/voices"
>
Browse and create voices for TTS
</Card>
</CardGroup>

## Installation

To use Voice.ai services, install the required dependencies:

```bash
pip install "pipecat-ai[voiceai]"
```

## Prerequisites

### Voice.ai Account Setup

Before using Voice.ai TTS services, you need:

1. **Voice.ai Account**: Sign up at [Voice.ai](https://voice.ai/)
2. **API Key**: Generate an API key from your account
3. **Voice Selection**: Choose a voice ID for synthesis

### Required Environment Variables

- `VOICEAI_API_KEY`: Your Voice.ai API key for authentication
- `VOICEAI_VOICE_ID`: (Optional) The voice identifier to use for TTS; omit for default voice