Overview of Model Offerings
This section provides some high-level context on Inworld’s model offerings, and how they can be used in your application.- TTS: Text-to-Speech models can be used to generate high-quality audio for your application, such as powering a character’s voice.
- LLM: Large Language Models are powerful models that can intake inputs (typically text, but certain models may also support other modalities) and generate text outputs. These models can be used to determine in-game actions, power conversations, generate dynamic narratives, and more.
- STT: Speech-to-Text models can be used to transcribe text from audio, powering voice-driven interactions and real-time transcription features in your application.
- Embeddings: Embeddings models convert text into high-dimensional vectors, which can be used to power intent detection, text similarity comparison, and retrieval-augmented generation (RAG).
TTS
Inworld’s Runtime and API offers access to Inworld’s family of state-of-the-art TTS models, optimized for different use cases, quality levels, and performance requirements. Support for additional TTS providers in Runtime is coming soon!
Inworld TTS 1.5 Max
Our flagship model, delivering the best balance of quality and speed
- Rich, expressive, contextually aware speech
- Support for 15 languages
- Optimized for real-time use (<200ms median latency)
- High quality instant voice cloning
Inworld TTS 1.5 Mini
Our ultra-fast, most cost-efficient model. For when latency is the top priority.
- Ultra-low latency (~120ms median latency)
- Support for 15 languages
- Radically affordable pricing
- High quality instant voice cloning
Models overview
| Name | Model ID | Description | Supported languages |
|---|---|---|---|
| Llama Inworld TTS 1.5 Max | inworld-tts-1.5-max | Flagship model, best balance of quality and speed | en, zh, ja, ko, ru, it, es, pt, fr, de, pl, nl, hi |
| Llama Inworld TTS 1.5 Mini | inworld-tts-1.5-mini | Ultra-fast, most cost-efficient model | en, zh, ja, ko, ru, it, es, pt, fr, de, pl, nl, hi |
| Llama Inworld TTS Max | inworld-tts-1-max | Our most powerful previous generation model, with timestamps support | en, de, es, fr, it, ja, ko, nl, pl, pt, ru, zh, hi |
| Llama Inworld TTS | inworld-tts-1 | Our fastest previous generation model, with timestamps support | en, de, es, fr, it, ja, ko, nl, pl, pt, ru, zh, hi |
LLM
Inworld’s SDKs and LLM API offers access to cloud-hosted LLMs via two endpoints, Text Completion and Chat Completion. To call a model, you’ll need to specify both the model name and the service provider, which is the provider hosting the model. Below is an overview of the available service providers and models, by endpoint.Chat Completion
| Provider | Model | |
|---|---|---|
| Anthropic | anthropic | Any Anthropic LLMs, such as: claude-opus-4-1 claude-opus-4-0 claude-sonnet-4-0 claude-3-5-haiku-latest |
| Fireworks | fireworks | Any Fireworks LLMs, such as: accounts/fireworks/models/gpt-oss-120b accounts/fireworks/models/gpt-oss-20b accounts/fireworks/models/deepseek-v3-0324 accounts/fireworks/models/llama4-maverick-instruct-basic |
| Google (Gemini) | Any Gemini LLMs, such as: gemini-2.5-pro gemini-2.5-flash gemini-2.5-flash-lite | |
| Groq | groq | Any Groq LLMs, such as gemma2-9b-it llama-3.1-8b-instant openai/gpt-oss-20b |
| Inworld | inworld | Coming soon |
| Mistral | mistral | ministral-8b-latest mistral-small-latest |
| OpenAI | openai | Any OpenAI LLMs, such as: gpt-5 gpt-5-mini gpt-4.1 o3 |
| Tenstorrent | tenstorrent | tenstorrent/Llama-3.3-70B-Instruct |
Text Completion
| Provider | Model | |
|---|---|---|
| Inworld | inworld | Coming soon |
| OpenAI | openai | OpenAI LLMs that support v1/completions endpoint, such as: davinci-002 |
STT
Support for additional STT models is coming soon!
| Provider | Model |
|---|---|
| Inworld | whisper-large-v3 |
Embeddings
| Provider | Model ID | Description | |
|---|---|---|---|
| Inworld | inworld | BAAI/bge-large-en-v1.5 | Great for English text |
| Inworld | inworld | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 | Great for multi-lingual text |
Terms of Service
You may not violate the terms of service or policies of third-party model providers using Inworld’s platform or your account will be subject to deactivation.- Cerebras: https://www.cerebras.ai/terms-of-service
- Anthropic: https://www.anthropic.com/legal/commercial-terms
- Fireworks: https://fireworks.ai/terms-of-service
- Google Vertex: https://cloud.google.com/terms/
- Groq: https://groq.com/terms-of-use
- Mistral: https://mistral.ai/terms/#terms-of-use
- OpenAI: https://openai.com/policies/row-terms-of-use/
- Tenstorrent: https://tenstorrent.com/terms