LogoAI Jet
Logo for Inworld AI

Inworld AI

Inworld AI provides a platform for building AI-powered characters and applications with advanced TTS and real-time LLM capabilities.

Introduction

Inworld AI is a comprehensive platform designed for developers and creators looking to integrate AI-driven characters and interactive experiences into their applications. It offers a suite of tools including:

  • Realtime TTS: High-quality, low-latency text-to-speech with multilingual support.
  • Realtime LLMs: Access to state-of-the-art Large Language Models for real-time applications.
  • Model-Agnostic Orchestration: Smart routing and orchestration layer for scalable AI solutions.
  • Multimodal Research: Open-source projects and research on multimodal AI models.

Key use cases include gaming, media, customer service, and voice agents, enabling developers to create engaging and responsive AI characters that can enhance user experiences and drive measurable improvements in engagement and retention.

Alternatives

  • Character.AI

    Character.AI offers a platform for creating and interacting with AI characters, providing similar conversational experiences and creative tools.

  • OpenAI (API)

    OpenAI provides powerful LLMs (like GPT) and advanced TTS capabilities that developers can use to build custom AI character systems from the ground up.

  • ElevenLabs

    ElevenLabs specializes in highly realistic AI voice synthesis and voice cloning, which is essential for creating believable and expressive AI characters.

  • Soul Machines

    Soul Machines focuses on creating lifelike 'Digital People' with advanced conversational AI and realistic animation, directly competing in the digital human space.

  • NVIDIA Omniverse ACE

    NVIDIA Omniverse ACE offers a modular framework for building and deploying AI-powered virtual assistants and digital humans, including speech AI and LLMs.

  • Google Cloud Dialogflow / Vertex AI Conversation

    Google Cloud provides enterprise-grade conversational AI tools for building sophisticated virtual agents and chatbots with robust LLM integration.

  • Azure AI Bot Service / Azure OpenAI Service

    Microsoft offers a comprehensive suite for developing conversational bots and leveraging powerful LLMs for interactive AI experiences.

  • Replika

    Replika is an AI companion app that focuses on personalized conversational AI and emotional connection, offering a user-facing alternative for interactive AI.

  • Hugging Face

    Hugging Face provides a vast ecosystem of open-source LLMs, TTS models, and tools for developers to build highly customizable AI character applications.

  • PolyAI

    PolyAI is an enterprise platform focused on building advanced voice assistants for customer service, utilizing sophisticated conversational AI for real-time interactions.

User Reviews

4.6/5.0
(6reviews)
Click stars to rate

Pricing

Pricing Model: Usage-based

Inworld-TTS-1

Text-to-Speech model.

$5/1M characters (~$0.005/minute)
usage-based
Inworld-TTS-1-Max

Advanced Text-to-Speech model.

$10/1M characters (~$0.01/minute)
usage-based
Inworld TTS on-prem

On-premise deployment available for Inworld-TTS-1 and Inworld-TTS-1-Max.

Contact for pricing
custom

Inworld Safety

Inworld's safety features for LLM.

Included
usage-based

Inworld Memory

Inworld's memory features for LLM.

Included
usage-based

Inworld Knowledge

Inworld's knowledge features for LLM.

Included
usage-based

gpt-oss 20B (Inworld On-prem)

LLM model provided by Inworld (On-prem).

Input Cost: -, Output Cost: Contact for pricing
custom
gemma3 12B (Inworld On-prem)

LLM model provided by Inworld (On-prem).

Input Cost: -, Output Cost: Contact for pricing
custom
gemma3 27B (Inworld On-prem)

LLM model provided by Inworld (On-prem).

Input Cost: -, Output Cost: Contact for pricing
custom
llama3.1 8B (Inworld On-prem)

LLM model provided by Inworld (On-prem).

Input Cost: -, Output Cost: Contact for pricing
custom
Voice Activity Detection (VAD) (Inworld On-prem)

Voice Activity Detection provided by Inworld (On-prem).

Included
usage-based

Claude Opus 4 (Anthropic)

LLM model provided by Anthropic.

Input: $15/1M tokens, Output: $75/1M tokens
usage-based
Claude Opus 4.1 (Anthropic)

LLM model provided by Anthropic.

Input: $15/1M tokens, Output: $75/1M tokens
usage-based
Claude Sonnet 4 (Anthropic)

LLM model provided by Anthropic.

Input: $3/1M tokens, Output: $15/1M tokens
usage-based
Claude 3.7 Sonnet (Anthropic)

LLM model provided by Anthropic.

Input: $3/1M tokens, Output: $15/1M tokens
usage-based
Claude 3 Haiku (Anthropic)

LLM model provided by Anthropic.

Input: $0.25/1M tokens, Output: $1.25/1M tokens
usage-based
Claude 3.5 Haiku (Anthropic)

LLM model provided by Anthropic.

Input: $0.8/1M tokens, Output: $4/1M tokens
usage-based
Gemini 2.5 Flash (Google)

LLM model provided by Google.

Input: $0.3/1M tokens, Output: $2.5/1M tokens
usage-based
Gemini 2.5 Pro ( <=200K input tokens) (Google)

LLM model provided by Google (Through Vertex AI).

Input: $1.25/1M tokens, Output: $10/1M tokens
usage-based
Gemini 2.5 Pro (>200K input tokens) (Google)

LLM model provided by Google (Through Vertex AI).

Input: $2.5/1M tokens, Output: $15/1M tokens
usage-based
Gemini 2.5 Flash Lite (Google)

LLM model provided by Google (Through Vertex AI).

Input: $0.1/1M tokens, Output: $0.4/1M tokens
usage-based
Gemini 2.0 Flash (Google)

LLM model provided by Google (Through Vertex AI).

Input: $0.1/1M tokens, Output: $0.4/1M tokens
usage-based
Gemini 2.0 Flash-Lite (Google)

LLM model provided by Google (Through Vertex AI).

Input: $0.075/1M tokens, Output: $0.3/1M tokens
usage-based
gpt-realtime (OpenAI)

LLM model provided by OpenAI.

Input: $4/1M tokens, Output: $16/1M tokens
usage-based
gpt-5 (OpenAI)

LLM model provided by OpenAI.

Input: $1.25/1M tokens, Output: $10/1M tokens
usage-based
gpt-5-mini (OpenAI)

LLM model provided by OpenAI.

Input: $0.25/1M tokens, Output: $2/1M tokens
usage-based
gpt-5-nano (OpenAI)

LLM model provided by OpenAI.

Input: $0.05/1M tokens, Output: $0.4/1M tokens
usage-based
gpt-5-chat-latest (OpenAI)

LLM model provided by OpenAI.

Input: $1.25/1M tokens, Output: $10/1M tokens
usage-based
gpt-4.1 (OpenAI)

LLM model provided by OpenAI.

Input: $2/1M tokens, Output: $8/1M tokens
usage-based
GPT-4.1 mini (OpenAI)

LLM model provided by OpenAI.

Input: $0.4/1M tokens, Output: $1.6/1M tokens
usage-based
GPT-4.1 nano (OpenAI)

LLM model provided by OpenAI.

Input: $0.1/1M tokens, Output: $0.4/1M tokens
usage-based
GPT-4o (OpenAI)

LLM model provided by OpenAI.

Input: $2.5/1M tokens, Output: $10/1M tokens
usage-based
gpt-4o-2024-05-13 (OpenAI)

LLM model provided by OpenAI.

Input: $5/1M tokens, Output: $15/1M tokens
usage-based
GPT-4o-mini (OpenAI)

LLM model provided by OpenAI.

Input: $0.15/1M tokens, Output: $0.6/1M tokens
usage-based
o1 (OpenAI)

LLM model provided by OpenAI.

Input: $15/1M tokens, Output: $60/1M tokens
usage-based
o1-pro (OpenAI)

LLM model provided by OpenAI.

Input: $150/1M tokens, Output: $600/1M tokens
usage-based
o3-pro (OpenAI)

LLM model provided by OpenAI.

Input: $20/1M tokens, Output: $80/1M tokens
usage-based
o3 (OpenAI)

LLM model provided by OpenAI.

Input: $2/1M tokens, Output: $8/1M tokens
usage-based
o4-mini (OpenAI)

LLM model provided by OpenAI.

Input: $1.1/1M tokens, Output: $4.4/1M tokens
usage-based
o3-mini (OpenAI)

LLM model provided by OpenAI.

Input: $1.1/1M tokens, Output: $4.4/1M tokens
usage-based
o1-mini (OpenAI)

LLM model provided by OpenAI.

Input: $1.1/1M tokens, Output: $4.4/1M tokens
usage-based
Mistral Small 3.2 (Mistral)

LLM model provided by Mistral.

Input: $0.1/1M tokens, Output: $0.3/1M tokens
usage-based
Ministral 8B 24.10 (Mistral)

LLM model provided by Mistral.

Input: $0.1/1M tokens, Output: $0.1/1M tokens
usage-based
DeepSeek V3.1 (Fireworks)

LLM model provided by Fireworks.

Input: $0.56/1M tokens, Output: $1.68/1M tokens
usage-based
Meta Llama 3.1 405B (Fireworks)

LLM model provided by Fireworks.

Input: $3/1M tokens, Output: $3/1M tokens
usage-based
Meta Llama 4 Maverick (Basic) (Fireworks)

LLM model provided by Fireworks.

Input: $0.22/1M tokens, Output: $0.88/1M tokens
usage-based
Meta Llama 3.2 3B Instruct (Fireworks)

LLM model provided by Fireworks.

Input: $0.1/1M tokens, Output: $0.1/1M tokens
usage-based
Meta Llama 3.1 8B Instruct (Fireworks)

LLM model provided by Fireworks.

Input: $0.2/1M tokens, Output: $0.2/1M tokens
usage-based
Meta Llama 3.3 70B Instruct (Fireworks)

LLM model provided by Fireworks.

Input: $0.9/1M tokens, Output: $0.9/1M tokens
usage-based
Qwen3 235B Family and GLM-4.5 Air (Fireworks)

LLM model provided by Fireworks.

Input: $0.22/1M tokens, Output: $0.88/1M tokens
usage-based
Kimi K2 Instruct (Fireworks)

LLM model provided by Fireworks.

Input: $0.6/1M tokens, Output: $2.5/1M tokens
usage-based
Qwen3 Coder 480B (Fireworks)

LLM model provided by Fireworks.

Input: $0.45/1M tokens, Output: $1.8/1M tokens
usage-based
OpenAI gpt OSS 120b (Fireworks)

LLM model provided by Fireworks.

Input: $0.15/1M tokens, Output: $0.6/1M tokens
usage-based
OpenAI gpt OSS 20b (Fireworks)

LLM model provided by Fireworks.

Input: $0.07/1M tokens, Output: $0.3/1M tokens
usage-based
GPT OSS 20B 128k (Groq)

LLM model provided by Groq.

Input: $0.1/1M tokens, Output: $0.5/1M tokens
usage-based
GPT OSS 120B 128k (Groq)

LLM model provided by Groq.

Input: $0.15/1M tokens, Output: $0.6/1M tokens
usage-based
Kimi K2 1T 256k (Groq)

LLM model provided by Groq.

Input: $1/1M tokens, Output: $3/1M tokens
usage-based
Llama 4 Scout (17Bx16E) 128k (Groq)

LLM model provided by Groq.

Input: $0.11/1M tokens, Output: $0.34/1M tokens
usage-based
Llama 4 Maverick (17Bx128E) 128k (Groq)

LLM model provided by Groq.

Input: $0.2/1M tokens, Output: $0.6/1M tokens
usage-based
Llama Guard 4 12B 128k (Groq)

LLM model provided by Groq.

Input: $0.2/1M tokens, Output: $0.2/1M tokens
usage-based
DeepSeek R1 Distill Llama 70B 128k (Groq)

LLM model provided by Groq.

Input: $0.75/1M tokens, Output: $0.99/1M tokens
usage-based
Qwen3 32B 131k (Groq)

LLM model provided by Groq.

Input: $0.29/1M tokens, Output: $0.59/1M tokens
usage-based
Mistral Saba 24B 32k (Groq)

LLM model provided by Groq.

Input: $0.79/1M tokens, Output: $0.79/1M tokens
usage-based
Llama 3.3 70B Versatile 128k (Groq)

LLM model provided by Groq.

Input: $0.59/1M tokens, Output: $0.79/1M tokens
usage-based
Llama 3.1 8B Instant 128k (Groq)

LLM model provided by Groq.

Input: $0.05/1M tokens, Output: $0.08/1M tokens
usage-based
Llama 3 70B 8k (Groq)

LLM model provided by Groq.

Input: $0.59/1M tokens, Output: $0.79/1M tokens
usage-based
Llama 3 8B 8k (Groq)

LLM model provided by Groq.

Input: $0.05/1M tokens, Output: $0.08/1M tokens
usage-based
Gemma 2 9B 8k (Groq)

LLM model provided by Groq.

Input: $0.2/1M tokens, Output: $0.2/1M tokens
usage-based
Llama Guard 3 8B 8k (Groq)

LLM model provided by Groq.

Input: $0.2/1M tokens, Output: $0.2/1M tokens
usage-based
Llama-3.3-70B-Instruct (Tenstorrent)

LLM model provided by Tenstorrent.

Input: $0.4/1M tokens, Output: $0.4/1M tokens
usage-based
Whisper-large-v3

Speech-to-Text (STT) model provided by OpenAI.

$0.0025 / min
usage-based

BAAI/bge-large-en-v1.5

Embedding model provided by Inworld.

$0.0023
usage-based

sentence-transformers/paraphrase-multilingual-mpnet-base-v2

Embedding model provided by Inworld.

$0.0007
usage-based

FAQ

More Products

Enterprise-grade Voice AI APIs for Speech-to-Text, Text-to-Speech, and Voice Agents, offering real-time, accurate, and scalable solutions.

Real-time engagement platform providing voice, video, and conversational AI APIs for developers to build interactive experiences.

Unified platform for AI voice, image, and video generation with flexible pricing and high-quality output, combining top technologies in one place.

Easy-to-use AI text-generation software for GGML and GGUF models, inspired by KoboldAI, offering a single, self-contained distributable.

Murf AI is a versatile AI voice generator and text-to-speech platform with realistic voices for various applications and API solutions.

Freed is an AI medical scribe that automates clinical documentation, saving clinicians time and improving note accuracy with EHR integration.

Abridge provides an enterprise-grade AI platform for clinical conversations, improving outcomes for clinicians, nurses, and revenue cycle teams.

AI-powered document conversion technology converting images and PDFs to LaTeX, DOCX, Markdown, Excel, and more.

Etaprise enhances productivity for home service businesses, managing appointments, AI scheduling, remote assistance, and payments.

AI-powered virtual receptionist software automating scheduling, answering calls, and lead capture for businesses 24/7.

Bizplanr is a FREE AI-powered business plan generator that helps entrepreneurs create professional business plans in minutes.

Mocha is an AI-powered no-code app builder that allows entrepreneurs to turn ideas into live websites and applications rapidly.

AI companion for mental, emotional, and spiritual well-being, empowering users to achieve happiness and thrive.

Aethera is an AI agent workspace designed for modern content teams, streamlining content workflows from brainstorming to delivery.

AI-powered tool to generate, schedule, and enhance social media posts with features like Dall-E image creation and grammar improvement.

Accelevents is an event management platform offering registration, badge printing, agenda management, and a mobile event app all-in-one.

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates