AI & Machine Learning
Connect LMNT to Your AI Agents
Let your Wkil agents generate natural speech and manage custom AI voices through LMNT.
Authentication: API key
What you can do
- Generate natural-sounding speech from text
- Create and manage custom AI voices
- Get word-level timing for synchronized playback
Available capabilities may vary by authentication and workspace configuration.
Actions supported by the connector
Synthesize Speech
Generate spoken audio from text using an LMNT AI voice.
Generate Speech With Metadata
Generate speech and return word-level timing metadata alongside the audio.
Get Voices List
Retrieve the list of available voices to choose from.
Create Voice
Train a custom voice from uploaded audio samples.
Get Voice Info
Retrieve metadata for a specific voice, including supported languages.
Practical agent use cases
- An agent converts a written response into spoken audio for a voice assistant reply.
- An agent generates narration with timing metadata to sync captions to audio.
How it works with Wkil
- 1Choose the integrationAdd LMNT to your agent from inside the Wkil platform.
- 2Grant the permissions it needsDefine precisely what the agent can access and perform.
- 3Test, then run itTest actions before they go live, with human approval where needed.
Permissions always stay in your control — you can scope access and require human approval before any sensitive action.
Related integrations
FAQ
Can I use a custom-trained voice?
Yes — a voice can be trained from your own audio samples and then used for synthesis.