Wit.ai integration
Natural Language Processing API by Meta. Extract intents and entities from text or speech. Build chatbots, voice assistants, and conversational AI applications.
Say what should happen.
The workflow builds itself.
Common Wit.ai use cases
- Model review
- Model cleanup
- Model training
- Entity inspection
- App management
- Training data management
- Chatbot NLU
- App overview
- Trait overview
- Entity overview
What you can do with Wit.ai
Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.
Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.
Intent, 4 operations
create_intentCreate intentPOSTCreates a new intent.delete_intentDelete intentDELETEDeletes an intent from the Wit.ai app.get_intentGet intentGETRetrieves details for a specific intent.list_intentsList intentsGETLists all intents in the Wit.ai app.
Nlp entity, 4 operations
delete_entityDelete entityDELETEDeletes an entity from the Wit.ai app.get_entityGet entityGETRetrieves details for a specific entity.list_entitiesList entitiesGETLists all entities in the Wit.ai app.update_entityUpdate entityPUTUpdates entity keywords and roles.
Trait, 4 operations
create_traitCreate traitPOSTCreates a new trait.delete_traitDelete traitDELETEDeletes a trait from the Wit.ai app.get_traitGet traitGETRetrieves details for a specific trait.list_traitsList traitsGETLists all traits in the Wit.ai app.
Utterance, 2 operations
delete_utterancesDelete utterancesDELETEDeletes training utterances from the model.train_utteranceTrain utterancePOSTTrains the model with new utterances.
App, 1 operation
list_appsList appsGETLists all Wit.ai apps for the authenticated user.
Dictation, 1 operation
transcribe_dictationTranscribe dictationPOSTTranscribes audio to text without NLU extraction.
Message, 1 operation
get_messageGet messageGETAnalyzes text to extract intents and entities.
Speech, 1 operation
speech_to_textSpeech to textPOSTTranscribes speech and extracts intents.
Speech synthesis, 1 operation
synthesize_speechSynthesize speechPOSTGenerates speech audio from text.
Voice, 1 operation
list_voicesList voicesGETLists available voices for speech synthesis.
Wit entity, 1 operation
create_entityCreate entityPOSTCreates a new custom entity.
Use Wit.ai from Claude Code, Cursor or Codex
Connect Wit.ai in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Wit.ai operations become tools the client can call, next to every other integration you connected.
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"
[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"{
"mcpServers": {
"livecontext": {
"type": "http",
"url": "https://livecontext.ai/mcp",
"headers": {
"X-API-Key": "YOUR_API_KEY"
}
}
}
}How to connect Wit.ai
- Create your workspace
Sign up free. Nothing to install.
- Connect Wit.ai once
Add your Wit.ai connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
- Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.
Wit.ai integration FAQ
What can you do with the Wit.ai integration?
LiveContext exposes 21 operations on Wit.ai, covering intent, nlp entity, trait and utterance. Common uses include Model review, Model cleanup and Model training.
