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
2 changes: 2 additions & 0 deletions docs.json
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,7 @@
"server/services/stt/gladia",
"server/services/stt/google",
"server/services/stt/groq",
"server/services/stt/hathora",
"server/services/stt/riva",
"server/services/stt/openai",
"server/services/stt/sambanova",
Expand Down Expand Up @@ -184,6 +185,7 @@
"server/services/tts/fish",
"server/services/tts/google",
"server/services/tts/groq",
"server/services/tts/hathora",
"server/services/tts/inworld",
"server/services/tts/lmnt",
"server/services/tts/minimax",
Expand Down
60 changes: 60 additions & 0 deletions server/services/stt/hathora.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,60 @@
---
title: "Hathora"
description: "Speech-to-text service implementations hosted on Hathora"
---

## Overview

Hathora is a hosting provider for several models for voice AI, including these STT service implementations:

- `ParakeetTDTSTTService` for NVIDIA's Parakeet TDT 0.6B model

<CardGroup cols={2}>
<Card
title="Hathora STT API Reference"
icon="code"
href="https://reference-server.pipecat.ai/en/latest/api/pipecat.services.hahotra.stt.html"
>
Pipecat's API methods for Hathora-hosted STT models
</Card>
<Card
title="Example Implementation"
icon="play"
href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/07f-interruptible-hathora.py"
>
Complete example using Hathora-hosted models
</Card>
<Card
title="Hathora Models Documentation"
icon="book"
href="https://models.hathora.dev/"
>
Official Hathora documentation and features
</Card>
</CardGroup>

## Installation

To use Hathora services, install the required dependencies:

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

## Prerequisites

### Hathora Account Setup

Before using Hathora STT services, you need:

1. **Hathora Account**: Sign up at [Hathora Models Console](https://models.hathora.dev/)
1. **API Key**: Generate an API token from your [Tokens page](https://models.hathora.dev/tokens)

### Hathora Model URL

Retrieve the `base_url` with these steps:

1. Clicking on the desired model [here](https://models.hathora.dev/)
1. Under **Input**, click the **API** tab
1. Click on the **cURL** (or **Basic (cURL)**) tab
1. The `base_url` is the full url seen after `curl -X POST`
1 change: 1 addition & 0 deletions server/services/supported-services.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,7 @@ Speech-to-Text services receive and audio input and output transcriptions.
| [Gladia](/server/services/stt/gladia) | `pip install "pipecat-ai[gladia]"` |
| [Google](/server/services/stt/google) | `pip install "pipecat-ai[google]"` |
| [Groq (Whisper)](/server/services/stt/groq) | `pip install "pipecat-ai[groq]"` |
| [Hathora](/server/services/stt/hathora) | `pip install "pipecat-ai[hathora]"` |
| [NVIDIA Riva](/server/services/stt/riva) | `pip install "pipecat-ai[riva]"` |
| [OpenAI (Whisper)](/server/services/stt/openai) | `pip install "pipecat-ai[openai]"` |
| [SambaNova (Whisper)](/server/services/stt/sambanova) | `pip install "pipecat-ai[sambanova]"` |
Expand Down
61 changes: 61 additions & 0 deletions server/services/tts/hathora.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,61 @@
---
title: "Hathora"
description: "Text-to-speech service implementations hosted on Hathora"
---

## Overview

Hathora is a hosting provider for several models for voice AI, including these TTS service implementations:

- `KokoroTTSService` for Hexgrad's Kokoro 82M model
- `ChatterboxTTSService` for Resemble AI's Chatterbox model

<CardGroup cols={2}>
<Card
title="Hathora TTS API Reference"
icon="code"
href="https://reference-server.pipecat.ai/en/latest/api/pipecat.services.hahotra.tts.html"
>
Pipecat's API methods for Hathora-hosted TTS models
</Card>
<Card
title="Example Implementation"
icon="play"
href="https://github.com/pipecat-ai/pipecat/blob/main/examples/foundational/07f-interruptible-hathora.py"
>
Complete example using Hathora-hosted models
</Card>
<Card
title="Hathora Models Documentation"
icon="book"
href="https://models.hathora.dev/"
>
Official Hathora documentation and features
</Card>
</CardGroup>

## Installation

To use Hathora services, install the required dependencies:

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

## Prerequisites

### Hathora Account Setup

Before using Hathora STT services, you need:

1. **Hathora Account**: Sign up at [Hathora Models Console](https://models.hathora.dev/)
1. **API Key**: Generate an API token from your [Tokens page](https://models.hathora.dev/tokens)

### Hathora Model URL

Retrieve the `base_url` with these steps:

1. Clicking on the desired model [here](https://models.hathora.dev/)
1. Under **Input**, click the **API** tab
1. Click on the **cURL** (or **Basic (cURL)**) tab
1. The `base_url` is the full url seen after `curl -X POST`