inworld

Plugin inworld from marketplace inworld in inworld-ai/plugin. Commands read from the repo's manifest — 5 days ago.

Skills (24)

• add-decisions

  Add probability-based classification, scoring and routing with Inworld Decisions. Use for model judgments that need confidence thresholds.

• add-llm

  Connect app LLM calls to Inworld inference and routing. Use for OpenAI/Anthropic-compatible integrations, model fallbacks or provider switches.

• add-realtime

  Build two-way voice agents with STT, LLM and TTS. Use for realtime conversations, phone agents, interruptions and tool calls.

• add-streaming-stt

  Add live captions or dictation with speaker labels, vocabulary hints and reliable final transcripts. Use for streaming audio, not recordings.

• add-streaming-tts

  Stream Inworld speech into an existing app or voice-agent loop. Use when playback should start before synthesis finishes.

• add-transcription

  Transcribe audio files and long recordings with speaker labels, timestamps and vocabulary hints. Use for meetings, podcasts and call archives.

• add-voice

  Add natural speech to one app feature with Inworld TTS. Use to select a voice, audition delivery and integrate speech output.

• benchmark-models

  Benchmark Inworld inference on your app's requests against its existing provider. Compare latency, cost and quality before choosing a model.

• benchmark-stt

  Benchmark speech recognition on recordings or live replays. Compare transcript accuracy, speaker labels, latency, failures and cost.

• configure-router

  Configure and test model routing, fallbacks and weighted A/B variants. Use for saved Inworld routers and conditional request routing.

• connect

  Connect your Inworld account using the coding agent's secure API-key settings. Use for first-time setup or missing credentials.

• custom-voice

  Prepare recordings for instant or professional voice cloning. Use for speaker isolation, training audio, IVC/PVC creation and integration.

• doctor

  Check Inworld configuration offline before making API calls. Use to inspect credentials, permissions, audio formats and streaming setup.

• find-voice

  Describe a voice and audition matches on your own script. Use for voice discovery, comparisons, custom voice design and delivery direction.

• generate-image

  Generate or edit images with Inworld's image models. Use for text-to-image, reference-guided edits and requested output comparisons.

• generate-video

  Generate videos and manage existing Inworld video jobs. Use for text or reference inputs, status checks, cancellation and downloads.

• latency

  Measure streaming speech latency and find bottlenecks in a voice app. Use for time to first audio, model selection and slow conversations.

• migrate

  Move an existing text-to-speech integration to Inworld. Use to map voices and formats, preserve a provider switch and verify the app's speech.

• pronunciation

  Create and test reusable pronunciation dictionaries for Inworld TTS. Use for brand names, specialist terms and consistent speech.

• setup

  Set up Inworld voice APIs in a project. Use for a first speech integration, reusable clients and working TTS or transcription examples.

• speakable-text

  Prepare LLM replies for speech with verbatim IDs, pronunciation, pauses and delivery tags. Use when spoken names or alphanumerics sound wrong.

• test-conversation

  Test voice conversations with offline scenarios and event-log checks. Use for interruptions, pauses, tool calls, reconnects and finalization.

• test-voice

  Catch speech regressions across voice, model, pronunciation and delivery changes. Use for frozen test lines, listening evidence and offline reports.

• troubleshoot

  Debug Inworld API errors using official docs and diagnostics. Use for authentication failures, unexpected responses and broken integrations.

MCP servers (1)

• inworld

  runs: node ${CLAUDE_PLUGIN_ROOT}/launcher.mjs

Similar plugins