Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.flowx.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

The Speech to Text node is a workflow node that transcribes audio files into text. It reads audio from a configured source, sends it to the speech-to-text service, and returns the transcript along with language detection and confidence metadata. The node works in both standard and conversational workflows, and integrates with the FlowX Document Plugin for file storage.
Speech to Text node configuration in Integration Designer

Transcribe audio

Convert audio recordings to text with language detection and confidence scores

Multiple file sources

Read audio from Document Plugin, S3, or directly from chat voice input

Chat integration

Automatically processes voice messages in conversational workflows

Test files for development

Upload sample audio to validate your workflow before connecting a live source

​
Configuration

1

Open your workflow

Open your workflow in Integration Designer.
2

Add the node

Add a Speech to Text node from the node palette.
3

Configure the settings

Configure the settings described below.

​
File Source

​
File Source
enum
required
Where the audio file is located.
SourceDescriptionAvailability
Document PluginRead audio from a file stored in the FlowX Document PluginStandard workflows
S3 ProtocolRead audio from S3-compatible storageStandard workflows
Chat InputAutomatically receive audio from a voice message in the chat UIConversational workflows only
In conversational workflows, the file source is set to Chat Input automatically.
Voice input configuration on a conversational workflow Start node
​
Use Test File
boolean
Upload and use a sample audio file for testing without connecting a live source. When turned on, File Path becomes a dropdown of available test files instead of a free-text input.Default: OFF
​
File Path
string
required
Path to the audio file. The control changes based on Use Test File:
  • Use Test File OFF — free-text input. Supports ${expression} placeholders for dynamic values from workflow data. Only meaningful when File Source is Document Plugin or S3 Protocol.
  • Use Test File ON — dropdown labelled Select Test File, listing the test files uploaded to this node.
Example: ${inputData.audioFilePath}
​
Response Key
string
required
The key under which the transcript and metadata are stored in the workflow data.Example: speechResult

​
Supported audio formats

FormatMIME Type
MP3audio/mpeg
WAVaudio/wav
M4Aaudio/x-m4a
AACaudio/aac
OGGaudio/ogg

​
File size limits

Workflow typeMaximum size
Conversational5 MB
Standard10 MB
Test files support the same audio formats listed above, with a maximum size of 15 MB.

​
Output

The node writes the transcript and metadata under the configured Response Key. Standard workflows output nested under the response key: 
{
  "responseKey": {
    "transcript": "The transcribed text content",
    "language": "en",
    "confidence": 1.0,
    "responseTime": 2.34,
    "audioFileName": "recording.mp3"
  }
}
Conversational workflows output at the top level for chat integration: 
{
  "userMessage": "The transcribed text content",
  "userMessageConfidence": 1.0
}
FieldTypeDescription
transcript / userMessagestringThe transcribed text
languagestringDetected language code (e.g., en, fr, de)
confidence / userMessageConfidencenumberConfidence score (0.0 to 1.0)
responseTimenumberProcessing time in seconds
audioFileNamestringOriginal audio file name

​
Conversational workflow integration

In conversational workflows, the Speech to Text node works with the Chat component voice input feature:
  1. A user records a voice message in the chat UI
  2. The audio file is sent to the workflow as a chat input
  3. The Speech to Text node (with Chat Input file source) transcribes the audio
  4. The transcript is set as the userMessage, making it available to downstream nodes (Custom Agent, Intent Classification) as if the user had typed it
When processing chat voice input, the audio file metadata is preserved in the conversation context. This allows conversation history to reference which messages originated from voice input.

​
Node connections

The Speech to Text node has two output handles:
HandleDescription
SuccessThe transcription completed and output is available under the response key
FailThe transcription failed (unsupported format, file not found, service error)
Connect downstream nodes to the appropriate handle to manage both successful and failed transcription scenarios.

​
Best practices

Match file source to workflow type

Use Chat Input for conversational workflows and Document Plugin or S3 for standard workflows.

Keep audio files within size limits

Audio files exceeding the size limit (5 MB conversational, 10 MB standard) will fail. Validate file size before reaching the node if the source is user-provided.

Use test files during development

Upload a sample audio file to validate your workflow configuration before connecting to a live source.

Handle failures

Always connect the Fail handle to a fallback path, especially when processing user-uploaded audio that may be in an unsupported format.

Chat component

Voice input and conversational UI for chat-based workflows

Conversational workflows

Build multi-turn conversations with AI Triggers and context

AI node types

Overview of all AI workflow node types

Integration Designer

Build and manage integration workflows
Last modified on June 2, 2026