Inworld

Overview

Inworld provides high-quality, low-latency speech synthesis via two implementation types: InworldTTSService for real-time, minimal-latency use-cases through websockets and InworldHttpTTSService for streaming and non-streaming use-cases over HTTP. Featuring support for 12+ languages, timestamps, custom pronunciation and instant voice cloning.

Models

The default model is Realtime TTS-2 (inworld-tts-2). Realtime TTS-1.5-Max (inworld-tts-1.5-max) and Realtime TTS-1.5-Mini (inworld-tts-1.5-mini) remain available.

Display name	Model ID
Realtime TTS-2 (default)	`inworld-tts-2`
Realtime TTS-1.5-Max	`inworld-tts-1.5-max`
Realtime TTS-1.5-Mini	`inworld-tts-1.5-mini`

Inworld TTS API Reference

Pipecat’s API methods for Inworld TTS integration

Example Implementation (Websockets)

Complete example with Inworld TTS

Inworld Documentation

Official Inworld TTS API documentation

Inworld Portal

Create and manage voice models

Installation

To use Inworld services, no additional dependencies are required beyond the base installation:

uv add "pipecat-ai"

Prerequisites

Inworld Account Setup

Before using Inworld TTS services, you need:

Inworld Account: Sign up at Inworld Studio
API Key: Generate an API key from your account dashboard
Voice Selection: Choose from available voice models

Required Environment Variables

INWORLD_API_KEY: Your Inworld API key for authentication

Configuration

InworldTTSService

WebSocket-based service for lowest latency streaming.

str

required

Inworld API key.

str

default:"Ashley"

deprecated

ID of the voice to use for synthesis. Deprecated in v0.0.105. Use settings=InworldTTSService.Settings(voice=...) instead.

str

default:"inworld-tts-2"

deprecated

ID of the model to use for synthesis. Deprecated in v0.0.105. Use settings=InworldTTSService.Settings(model=...) instead.

str

URL of the Inworld WebSocket API.

int

default:"None"

Audio sample rate in Hz. When None, uses the pipeline’s configured sample rate.

str

default:"PCM"

Audio encoding format.

TextAggregationMode

default:"TextAggregationMode.SENTENCE"

Controls how incoming text is aggregated before synthesis. SENTENCE (default) buffers text until sentence boundaries, producing more natural speech. TOKEN streams tokens directly for lower latency. Import from pipecat.services.tts_service.

bool

default:"None"

deprecated

Deprecated in v0.0.104. Use text_aggregation_mode instead.

bool

default:"True"

Whether to append a trailing space to text before sending to TTS.

InputParams

default:"None"

deprecated

Deprecated in v0.0.105. Use settings=InworldTTSService.Settings(...) instead.

InworldTTSService.Settings

default:"None"

Runtime-configurable settings. See InworldTTSService Settings below.

InworldTTSService Settings

Runtime-configurable settings passed via the settings constructor argument using InworldTTSService.Settings(...). These can be updated mid-conversation with TTSUpdateSettingsFrame. See Service Settings for details.

Parameter	Type	Default	Description
`model`	`str`	`None`	Model identifier. (Inherited.)
`voice`	`str`	`None`	Voice identifier. (Inherited.)
`language`	`Language \| str`	`None`	Language for synthesis. (Inherited.)
`speaking_rate`	`float`	`NOT_GIVEN`	Speaking rate for speech synthesis.
`temperature`	`float`	`NOT_GIVEN`	Temperature for speech synthesis.
`delivery_mode`	`"STABLE" \| "BALANCED" \| "CREATIVE"`	`NOT_GIVEN`	Controls the stability vs. creativity tradeoff. `"STABLE"` produces reliable, predictable speech. `"BALANCED"` is the default midpoint. `"CREATIVE"` produces more expressive, emotionally varied speech. Only supported by `inworld-tts-2`.

InworldHttpTTSService

HTTP-based service supporting both streaming and non-streaming modes.

str

required

Inworld API key.

aiohttp.ClientSession

required

aiohttp ClientSession for HTTP requests.

str

default:"Ashley"

deprecated

ID of the voice to use for synthesis. Deprecated in v0.0.105. Use settings=InworldHttpTTSService.Settings(voice=...) instead.

str

default:"inworld-tts-2"

deprecated

ID of the model to use for synthesis. Deprecated in v0.0.105. Use settings=InworldHttpTTSService.Settings(model=...) instead.

bool

default:"True"

Whether to use streaming mode.

int

default:"None"

Audio sample rate in Hz.

str

default:"PCM"

Audio encoding format.

InputParams

default:"None"

deprecated

Deprecated in v0.0.105. Use settings=InworldHttpTTSService.Settings(...) instead.

InworldHttpTTSService.Settings

default:"None"

Runtime-configurable settings. See InworldTTSService Settings below.

Usage

Basic Setup (WebSocket)

from pipecat.services.inworld import InworldTTSService

tts = InworldTTSService(
    api_key=os.getenv("INWORLD_API_KEY"),
    settings=InworldTTSService.Settings(
        voice="Ashley",
    ),
)

With Custom Settings

tts = InworldTTSService(
    api_key=os.getenv("INWORLD_API_KEY"),
    settings=InworldTTSService.Settings(
        voice="Ashley",
        model="inworld-tts-2",
        temperature=0.8,
        speaking_rate=1.1,
    ),
)

HTTP Service

import aiohttp
from pipecat.services.inworld import InworldHttpTTSService

async with aiohttp.ClientSession() as session:
    tts = InworldHttpTTSService(
        api_key=os.getenv("INWORLD_API_KEY"),
        aiohttp_session=session,
        voice_id="Ashley",
        streaming=True,
    )

The InputParams / params= pattern is deprecated as of v0.0.105. Use Settings / settings= instead. See the Service Settings guide for migration details.

Notes

WebSocket vs HTTP: The WebSocket service (InworldTTSService) provides the lowest latency with bidirectional streaming and supports multiple independent audio contexts per connection (max 5). The HTTP service supports both streaming and non-streaming modes via the streaming parameter.
Word timestamps: Both services provide word-level timestamps for synchronized text display. Timestamps are tracked cumulatively across utterances within a turn. When timestamps are not received from the service, a fallback mechanism ensures the full text is still committed to the LLM conversation context, even on interruption.
Auto mode: When auto_mode=True (default), the server controls flushing of buffered text for optimal latency and quality. This is recommended when text is sent in full sentences or phrases (i.e., when using text_aggregation_mode=TextAggregationMode.SENTENCE).
Keepalive: The WebSocket service sends periodic keepalive messages every 60 seconds to maintain the connection.

Event Handlers

Inworld TTS supports the standard service connection events:

Event	Description
`on_connected`	Connected to Inworld WebSocket
`on_disconnected`	Disconnected from Inworld WebSocket
`on_connection_error`	WebSocket connection error occurred

@tts.event_handler("on_connected")
async def on_connected(service):
    print("Connected to Inworld")

Pipecat Server

Client SDKs

Pipecat Flows

Pipecat Cloud

CLI

Pipecat Context Hub

Overview

Models

Inworld TTS API Reference

Example Implementation (Websockets)

Inworld Documentation

Inworld Portal

Installation

Prerequisites

Inworld Account Setup

Required Environment Variables

Configuration

InworldTTSService

InworldTTSService Settings

InworldHttpTTSService

Usage

Basic Setup (WebSocket)

With Custom Settings

HTTP Service

Notes

Event Handlers

​Overview

​Models

Inworld TTS API Reference

Example Implementation (Websockets)

Inworld Documentation

Inworld Portal

​Installation

​Prerequisites

​Inworld Account Setup

​Required Environment Variables

​Configuration

​InworldTTSService

​InworldTTSService Settings

​InworldHttpTTSService

​Usage

​Basic Setup (WebSocket)

​With Custom Settings

​HTTP Service

​Notes

​Event Handlers

Overview

Models

Installation

Prerequisites

Inworld Account Setup

Required Environment Variables

Configuration

InworldTTSService

InworldTTSService Settings

InworldHttpTTSService

Usage

Basic Setup (WebSocket)

With Custom Settings

HTTP Service

Notes

Event Handlers