Voice
Trigger workflows with voice input — records audio, transcribes with a speech-to-text model, and surfaces relevant knowledge base context.
The Voice Trigger block lets users start a workflow by speaking. It records audio from the browser, transcribes it using your configured speech-to-text (STT) provider, and optionally retrieves relevant context from a knowledge base before the workflow continues.
Configuration
| Field | Required | Description |
|---|---|---|
| STT Provider | Yes | The speech-to-text integration to use for transcription. Must be an installed STT-capable integration. |
| Model | Yes | The specific model offered by the selected provider. Options are populated after you pick a provider. |
| Language | No | Force a specific transcription language. Defaults to auto-detect. |
| Knowledge Base | No | A knowledge base to search using the transcript. Relevant items are returned as structured context. |
| Max KB Results | No | Maximum number of knowledge base items to surface. Defaults to 5. |
Outputs
Once transcription and (optional) KB retrieval complete, the following variables are available in downstream blocks:
| Variable | Type | Description |
|---|---|---|
<voice1.transcript> | string | The transcribed text from the audio recording |
<voice1.knowledgeBaseItems> | JSON array | Matched knowledge base items (empty array if no KB is configured) |
<voice1.knowledgeBaseContext> | string | Matched KB items formatted as a single context string, ready to pass to an LLM |
<voice1.audioUrl> | string | Presigned URL to download the original audio file |
<voice1.language> | string | Detected or configured language code (e.g. en, fr) |
<voice1.duration> | number | Audio duration in seconds |
Replace voice1 with the name you assigned to the block.
Deployment
The Voice Trigger generates a shareable Trigger Link (format: /v/{id}) once the workflow is deployed. Share that link with users — opening it in a browser presents the voice recording interface and starts a workflow run when audio is submitted.
A Speech-to-Text integration must be installed and configured in your workspace before the Voice Trigger can transcribe audio. See Integrations to add an STT provider.