Inworld AI

aid: inworld-ai
url: https://raw.githubusercontent.com/api-evangelist/inworld-ai/refs/heads/main/apis.yml
name: Inworld AI
apis:
- aid: inworld-ai:inworld-tts-api
  name: Inworld TTS API
  tags:
  - AI
  - Artificial Intelligence
  - Text To Speech
  - Voice
  - Audio
  humanURL: https://docs.inworld.ai/tts/tts
  properties:
  - url: https://docs.inworld.ai/tts/tts
    type: Documentation
  - url: https://docs.inworld.ai/quickstart-tts
    type: GettingStarted
  - url: https://docs.inworld.ai/api-reference/ttsAPI/texttospeech/synthesize-speech
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/ttsAPI/texttospeech/synthesize-speech-stream
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/ttsAPI/texttospeech/synthesize-speech-websocket
    type: Documentation
  - url: https://docs.inworld.ai/tts/voice-cloning
    type: Documentation
  - url: https://docs.inworld.ai/tts/voice-design
    type: Documentation
  - url: https://docs.inworld.ai/tts/on-premises
    type: Documentation
  - url: openapi/inworld-tts-api-openapi.yml
    type: OpenAPI
  - url: asyncapi/inworld-ai-asyncapi.yml
    type: AsyncAPI
  - url: json-schema/inworld-tts-synthesis-schema.json
    type: JSONSchema
  - url: json-ld/inworld-ai-context.jsonld
    type: JSONLD
  description: >-
    Inworld TTS — real-time text-to-speech API with the #1-ranked voice models on the Artificial Analysis
    Speech Arena. Supports the Realtime TTS-2 model (100+ languages, natural-language steering), Realtime TTS
    1.5 Max (15 languages), and Realtime TTS 1.5 Mini (cost-optimized, sub-120 ms first-token). Provides
    synchronous synthesis, server-streamed synthesis, and a streaming WebSocket interface with instant +
    professional voice cloning, voice design from text prompts, custom pronunciation, pause controls,
    word/character/phoneme alignment for lipsync, and zero-data-retention plus on-premise deployment options.
- aid: inworld-ai:inworld-voice-api
  name: Inworld Voice API
  tags:
  - AI
  - Artificial Intelligence
  - Voice
  - Voice Cloning
  - Voice Design
  humanURL: https://docs.inworld.ai/api-reference/voiceAPI/voiceservice/list-voices
  properties:
  - url: https://docs.inworld.ai/tts/voice-cloning
    type: Documentation
  - url: https://docs.inworld.ai/tts/voice-design
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/voiceAPI/voiceservice/clone-voice
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/voiceAPI/voiceservice/design-voice
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/voiceAPI/voiceservice/publish-voice
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/voiceAPI/voiceservice/list-voices
    type: Documentation
  - url: openapi/inworld-voice-api-openapi.yml
    type: OpenAPI
  description: >-
    Inworld Voice API — manage custom voices used by the TTS and Realtime APIs. Clone voices from short audio
    samples (instant voice cloning) or design voices from natural-language descriptions plus optional
    reference audio. Lists, gets, updates, and deletes voices, and exposes a publish endpoint for sharing
    voices across a workspace.
- aid: inworld-ai:inworld-stt-api
  name: Inworld STT API
  tags:
  - AI
  - Artificial Intelligence
  - Speech To Text
  - Transcription
  - Voice
  humanURL: https://docs.inworld.ai/stt/overview
  properties:
  - url: https://docs.inworld.ai/stt/overview
    type: Documentation
  - url: https://docs.inworld.ai/stt/quickstart
    type: GettingStarted
  - url: https://docs.inworld.ai/api-reference/sttAPI/speechtotext/transcribe
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/sttAPI/speechtotext/transcribe-stream-websocket
    type: Documentation
  - url: https://docs.inworld.ai/stt/voice-profiles
    type: Documentation
  - url: openapi/inworld-stt-api-openapi.yml
    type: OpenAPI
  - url: asyncapi/inworld-ai-asyncapi.yml
    type: AsyncAPI
  description: >-
    Inworld STT — speech-to-text transcription API with synchronous transcribe and a streaming WebSocket
    endpoint. Multi-provider routing (currently Whisper variants via Groq) with 99+ language support, word
    timestamps, voice profiling, prompt biasing for domain-specific vocabulary, and configurable end-of-turn
    detection for low-latency conversational agents.
- aid: inworld-ai:inworld-realtime-api
  name: Inworld Realtime API
  tags:
  - AI
  - Artificial Intelligence
  - Realtime
  - Voice
  - WebSocket
  - WebRTC
  humanURL: https://docs.inworld.ai/realtime/overview
  properties:
  - url: https://docs.inworld.ai/realtime/overview
    type: Documentation
  - url: https://docs.inworld.ai/realtime/quickstart-websocket
    type: GettingStarted
  - url: https://docs.inworld.ai/realtime/quickstart-webrtc
    type: GettingStarted
  - url: https://docs.inworld.ai/api-reference/realtimeAPI/realtime/realtime-websocket
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/realtimeAPI/realtime/realtime-webrtc
    type: Documentation
  - url: https://docs.inworld.ai/realtime/openai-migration
    type: Documentation
  - url: https://docs.inworld.ai/realtime/usage/twilio
    type: Documentation
  - url: openapi/inworld-realtime-api-openapi.yml
    type: OpenAPI
  - url: asyncapi/inworld-ai-asyncapi.yml
    type: AsyncAPI
  description: >-
    Inworld Realtime — end-to-end speech-to-speech voice pipeline (STT + LLM + TTS) exposed over WebSocket
    and WebRTC. OpenAI-Realtime-API-compatible event protocol (session.update, input_audio_buffer.append,
    response.create, etc.) so existing OpenAI Realtime clients can swap base URLs. Includes server-side and
    semantic VAD, function/tool calling, MCP server tunneling, Twilio media-stream integration, and JWT-based
    session authentication.
- aid: inworld-ai:inworld-router-api
  name: Inworld LLM Router API
  tags:
  - AI
  - Artificial Intelligence
  - LLM
  - Routing
  - OpenAI Compatible
  humanURL: https://docs.inworld.ai/router/introduction
  properties:
  - url: https://docs.inworld.ai/router/introduction
    type: Documentation
  - url: https://docs.inworld.ai/router/quickstart
    type: GettingStarted
  - url: https://docs.inworld.ai/router/openai-compatibility
    type: Documentation
  - url: https://docs.inworld.ai/router/anthropic-compatibility
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/routerAPI/chat-completions
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/routerAPI/routerservice/create-router
    type: Documentation
  - url: https://docs.inworld.ai/api-reference/routerAPI/routerservice/list-routers
    type: Documentation
  - url: https://docs.inworld.ai/router/capabilities/provider-routing
    type: Documentation
  - url: https://docs.inworld.ai/router/capabilities/conditional-routing
    type: Documentation
  - url: https://docs.inworld.ai/router/capabilities/traffic-splitting
    type: Documentation
  - url: https://docs.inworld.ai/router/capabilities/caching
    type: Documentation
  - url: https://docs.inworld.ai/router/capabilities/web-search
    type: Documentation
  - url: https://docs.inworld.ai/router/capabilities/prompt-compression
    type: Documentation
  - url: https://docs.inworld.ai/router/guides/claude-code
    type: Documentation
  - url: openapi/inworld-router-api-openapi.yml
    type: OpenAPI
  - url: json-schema/inworld-router-chat-completion-schema.json
    type: JSONSchema
  description: >-
    Inworld LLM Router — OpenAI-and-Anthropic-compatible chat-completions endpoint that routes prompts across
    hundreds of provider models (OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, Groq, etc.). Reusable
    named routers, conditional routing, provider routing, A/B traffic splitting, prompt compression, caching,
    web search, and a Claude-Code-compatible mode let teams consolidate model spend behind one API.
- aid: inworld-ai:inworld-models-api
  name: Inworld Models API
  tags:
  - AI
  - Artificial Intelligence
  - Models
  - Discovery
  humanURL: https://docs.inworld.ai/api-reference/modelsAPI/modelservice/list-models
  properties:
  - url: https://docs.inworld.ai/api-reference/modelsAPI/modelservice/list-models
    type: Documentation
  - url: openapi/inworld-models-api-openapi.yml
    type: OpenAPI
  description: >-
    Inworld Models API — list every model available across the Router (third-party LLMs) and Inworld
    first-party TTS, STT, and Realtime endpoints. Returns provider, model id, capabilities (chat, vision,
    tool use, etc.), and pricing tier metadata for runtime discovery.
tags:
- AI
- Artificial Intelligence
- Voice
- Text To Speech
- Speech To Text
- Realtime
- LLM Routing
- Voice Cloning
- Conversational AI
- Game AI
kind: contract
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
access: 3rd-Party
common:
- url: https://inworld.ai
  type: Portal
- url: https://docs.inworld.ai
  type: Documentation
- url: https://docs.inworld.ai/introduction
  name: Hello Inworld
  type: GettingStarted
- url: https://docs.inworld.ai/api-reference/introduction
  name: API Reference
  type: Documentation
- url: https://docs.inworld.ai/llms.txt
  name: LLM-Friendly Documentation Index
  type: Documentation
- url: https://docs.inworld.ai/llms-full.txt
  name: Full Documentation Archive
  type: Documentation
- url: https://platform.inworld.ai
  name: Inworld Portal
  type: SignUp
- url: https://platform.inworld.ai/api-keys
  name: API Keys
  type: Authentication
- url: https://platform.inworld.ai/tts-playground
  name: TTS Playground
  type: Sandbox
- url: https://status.inworld.ai
  type: StatusPage
- url: https://github.com/inworld-ai
  type: GitHubOrganization
- url: https://github.com/inworld-ai/tts
  name: Inworld TTS Open Models
  type: SourceCode
- url: https://github.com/inworld-ai/inworld-api-examples
  name: API Examples
  type: CodeExamples
- url: https://github.com/inworld-ai/inworld-nodejs-jwt-sample-app
  name: Node.js JWT Sample App
  type: CodeExamples
- url: https://github.com/inworld-ai/inworld-runtime-templates-node
  name: Inworld Runtime Templates (Node)
  type: CodeExamples
- url: https://github.com/inworld-ai/voice-agent-node
  name: Voice Agent Template (Node)
  type: CodeExamples
- url: https://github.com/inworld-ai/voice-agent-avatar-node
  name: Voice + Avatar Agent (Node + HeyGen)
  type: CodeExamples
- url: https://github.com/inworld-ai/livekit_agents
  name: LiveKit Agents Integration (Python)
  type: SDK
- url: https://github.com/inworld-ai/livekit_agents_js
  name: LiveKit Agents Integration (JS)
  type: SDK
- url: https://github.com/inworld-ai/pipecat
  name: Pipecat Integration
  type: SDK
- url: https://github.com/inworld-ai/langchain-voice-agent-node
  name: LangChain Voice Agent (Node)
  type: CodeExamples
- url: https://github.com/inworld-ai/voice-migration-tool
  name: ElevenLabs Voice Migration Tool
  type: Tool
- url: https://github.com/inworld-ai/inworld-tts-onprem
  name: TTS On-Premise
  type: Tool
- url: https://github.com/inworld-ai/multimodal-companion-node
  name: Multimodal Companion Demo
  type: CodeExamples
- url: https://github.com/inworld-ai/runtime-multimodal-companion-unity
  name: Multimodal Companion Unity Client
  type: CodeExamples
- url: https://github.com/inworld-ai/living-memories-node
  name: Living Memories (Node)
  type: CodeExamples
- url: https://github.com/inworld-ai/living-memories-unity
  name: Living Memories (Unity)
  type: CodeExamples
- url: https://github.com/inworld-ai/comic-generator-node
  name: Comic Generator Demo
  type: CodeExamples
- url: https://github.com/inworld-ai/greeting-card-node
  name: Greeting Card Generator Demo
  type: CodeExamples
- url: https://github.com/inworld-ai/zoom-demeanor-evaluator-node
  name: Zoom Demeanor Evaluator
  type: CodeExamples
- url: https://github.com/inworld-ai/language-learning-node
  name: Language Learning Demo
  type: CodeExamples
- url: https://github.com/inworld-ai/llm-to-tts-node
  name: LLM-to-TTS Pipeline (CLI)
  type: CodeExamples
- url: https://github.com/inworld-ai/runtime-chat-with-docs
  name: Chat With Docs Demo
  type: CodeExamples
- url: https://docs.inworld.ai/resources/rate-limits
  type: RateLimits
- url: https://docs.inworld.ai/tts/resources/billing
  name: TTS Billing
  type: Pricing
- url: https://docs.inworld.ai/stt/resources/billing
  name: STT Billing
  type: Pricing
- url: https://docs.inworld.ai/realtime/resources/billing
  name: Realtime Billing
  type: Pricing
- url: https://docs.inworld.ai/router/resources/billing
  name: Router Billing
  type: Pricing
- url: https://docs.inworld.ai/portal/billing
  type: Pricing
- url: https://docs.inworld.ai/portal/usage
  type: Documentation
- url: https://docs.inworld.ai/tts/resources/zero-data-retention
  name: Zero Data Retention
  type: Security
- url: https://docs.inworld.ai/tts/on-premises
  name: On-Premise Deployment
  type: Deployment
- url: https://docs.inworld.ai/release-notes/tts
  name: TTS Release Notes
  type: ChangeLog
- url: https://docs.inworld.ai/tts/resources/elevenlabs-migration
  name: ElevenLabs Migration
  type: Migration
- url: https://docs.inworld.ai/router/migration/openrouter-to-inworld
  name: OpenRouter Migration
  type: Migration
- url: https://docs.inworld.ai/router/migration/anthropic-to-inworld
  name: Anthropic Migration
  type: Migration
- url: https://docs.inworld.ai/tts/resources/support
  type: Support
- url: https://inworld.ai/pricing
  type: Pricing
  data:
  - id: on-demand
    name: On-Demand
    entries:
    - geo: US
      unit: 1
      label: Account
      limit: 1
      price: 0
      metric: account
      timeFrame: month
      description: Free entry tier with up to 40 minutes of TTS included.
    elements:
    - name: Up to 40 min of TTS included
    - name: 5 custom voices
    - name: Realtime TTS-2 and 1.5 Max at $35 / 1M characters
    - name: Realtime TTS 1.5 Mini at $25 / 1M characters
    - name: STT at $0.35 per audio hour
    - name: LLM Router billed at provider cost
    description: Try Inworld at no commitment.
  - id: creator
    name: Creator
    entries:
    - geo: US
      unit: 1
      label: Account
      limit: 1
      price: 25
      metric: account
      timeFrame: month
      description: Small projects tier with $25 in monthly credits.
    elements:
    - name: $25 credits/month
    - name: 100 custom voices
    - name: Audio downloads
    description: Small projects.
  - id: developer
    name: Developer
    entries:
    - geo: US
      unit: 1
      label: Account
      limit: 1
      price: 300
      metric: account
      timeFrame: month
      description: Production tier with $300 monthly credits and up to 20% off rates.
    elements:
    - name: $300 credits/month
    - name: Up to 20% off rates
    - name: 1,000 custom voices
    description: Production applications.
  - id: growth
    name: Growth
    entries:
    - geo: US
      unit: 1
      label: Account
      limit: 1
      price: 1500
      metric: account
      timeFrame: month
      description: High-volume tier with $1,500 monthly credits and up to 40% off rates.
    elements:
    - name: $1,500 credits/month
    - name: Up to 40% off rates
    - name: 3,000 custom voices
    description: High-volume deployments.
  - id: enterprise
    name: Enterprise
    entries:
    - geo: US
      unit: 1
      label: Account
      limit: 1
      price: Call
      metric: account
      timeFrame: month
      description: Custom contract with negotiated rates and on-prem options.
    elements:
    - name: Rates as low as $10 / 1M for Realtime TTS-2 & 1.5 Max
    - name: $5 / 1M for Realtime TTS 1.5 Mini
    - name: On-prem deployment
    - name: Data residency
    - name: Zero data retention
    description: Enterprise commercial terms.
- url: https://inworld.ai/pricing
  type: Plans
  name: Plans
- url: https://plans/inworld-ai-plans-pricing.yml
  type: Plans
- url: https://rate-limits/inworld-ai-rate-limits.yml
  type: RateLimits
- url: https://finops/inworld-ai-finops.yml
  type: FinOps
- type: Features
  data:
  - Realtime TTS-2 voice model — 100+ languages, natural-language steering, sub-200ms first-token latency
  - Realtime TTS 1.5 Max — #1 on the Artificial Analysis Speech Arena (ELO ~1,238, April 2026)
  - Realtime TTS 1.5 Mini — cost-optimized voice with ~120ms first-token latency
  - Instant voice cloning from short audio samples
  - Professional voice cloning with audio processing controls
  - Voice design from natural-language descriptions plus optional reference audio
  - Word-, character-, and phoneme-level alignment (visemes) for lipsync and avatar rendering
  - Custom pronunciation, pause controls, voice tags, and long-text streaming synthesis
  - WebSocket TTS for bidirectional streaming synthesis
  - Speech-to-Text via multi-provider routing (Whisper variants on Groq) with 99+ languages, prompt
    biasing, word timestamps, and configurable end-of-turn detection
  - Realtime API — speech-to-speech pipeline over WebSocket and WebRTC, OpenAI-Realtime compatible
  - Twilio media-stream integration for inbound and outbound phone calls
  - MCP server tunneling inside Realtime sessions
  - JWT-based realtime authentication (separate Realtime-only API keys)
  - LLM Router — OpenAI-and-Anthropic-compatible chat-completions over hundreds of provider models
  - Named reusable routers with conditional routing, A/B traffic splitting, and provider routing
  - Prompt caching, prompt compression, and integrated web search inside the Router
  - Claude-Code-compatible mode for drop-in Claude Code substitution
  - Zero Data Retention (ZDR) option for TTS and Realtime
  - On-premise TTS deployment for regulated and air-gapped environments
  - ElevenLabs voice-migration tool for batch-importing voice clones
  - Open-source Python TTS model in the inworld-ai/tts repository
  - Integrations with LiveKit Agents, Pipecat, LangChain, and HeyGen avatars
  - Unity-side runtime templates for game and avatar use cases
  sources:
  - https://inworld.ai
  - https://inworld.ai/pricing
  - https://docs.inworld.ai/llms.txt
  - https://docs.inworld.ai/api-reference/introduction
  - https://github.com/inworld-ai
  updated: '2026-05-25'
created: '2026-05-25T00:00:00.000Z'
modified: '2026-05-25'
position: Consuming
description: >-
  Inworld AI is a real-time voice AI infrastructure provider. The Inworld platform delivers text-to-speech,
  speech-to-text, an end-to-end speech-to-speech Realtime API, and an OpenAI- and Anthropic-compatible LLM
  Router behind one API surface and one billing relationship. Inworld's voice models lead the Artificial
  Analysis Speech Arena and are used to power voice agents, language-learning apps, AI companions, avatar
  experiences, game NPCs, and Twilio-backed phone agents. The platform supports instant and professional
  voice cloning, voice design from natural language, lipsync-grade phoneme alignment, on-premise TTS
  deployment, and zero-data-retention configurations for regulated workloads.
maintainers:
- FN: Kin Lane
  email: info@apievangelist.com
  X: apievangelist
  url: https://apievangelist.com
specificationVersion: '0.16'