Hathora

Text-to-speech service implementations hosted on Hathora

Overview

Hathora is a hosting provider for several models for voice AI, which can be utilized under the single HathoraTTSService.

Hathora TTS API Reference

Pipecat’s API methods for Hathora-hosted TTS models

Example Implementation

Complete example using Hathora-hosted models

Hathora Models Documentation

Official Hathora documentation and features

Installation

To use Hathora services, install the required dependencies:

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
2. API Key: Generate an API token from your Tokens page

Hathora Model Specifier

The HathoraTTSService accepts a model: str parameter which corresponds to the model you would like to use.

You can find available specifiers here

Configuration

HathoraTTSService

model · str · required

Model to use. Find available models at models.hathora.dev.

voice_id · str · default: "None"

Voice to use for synthesis (if supported by model).

sample_rate · int · default: "None"

Output sample rate for generated audio. When None, uses the pipeline’s configured sample rate.

api_key · str · default: "None"

API key for authentication. If None, uses the HATHORA_API_KEY environment variable.

base_url · str · default: "https://api.models.hathora.dev/inference/v1/tts"

Base API URL for the Hathora TTS service.

params · InputParams · default: "None"

Runtime-configurable settings. See InputParams below.

InputParams

Configuration settings that can be set at initialization via the params constructor argument.

Parameter	Type	Default	Description
speed	float	None	Speech speed multiplier (if supported by model).
config	list[ConfigOption]	None	Additional model-specific configuration options. Each ConfigOption has name and value fields. Refer to Hathora docs for supported options per model.

Usage

Basic Setup

from pipecat.services.hathora import HathoraTTSService

tts = HathoraTTSService(
    model="your-model-specifier",
    api_key=os.getenv("HATHORA_API_KEY"),
)

With Voice and Speed

tts = HathoraTTSService(
    model="your-model-specifier",
    voice_id="some-voice",
    api_key=os.getenv("HATHORA_API_KEY"),
    params=HathoraTTSService.InputParams(
        speed=1.2,
    ),
)

With Model-Specific Config

from pipecat.services.hathora.utils import ConfigOption

tts = HathoraTTSService(
    model="your-model-specifier",
    api_key=os.getenv("HATHORA_API_KEY"),
    params=HathoraTTSService.InputParams(
        config=[
            ConfigOption(name="option_name", value="option_value"),
        ],
    ),
)

Notes

• Multi-model support: Hathora hosts several different TTS models under a single API. The model parameter determines which model is used.
• Audio format handling: The service automatically detects whether the response is WAV or raw PCM and handles both formats transparently.
• Model-specific features: Not all models support all features (e.g., voice_id, speed, config). Refer to the Hathora documentation for model-specific capabilities.