Skip to main content
Available starting with FlowX.AI 5.7.0

​
Overview

The Speech to Text node is a workflow node that converts between audio and text. It supports two operations: Transcribe converts audio files into text, and Text to Speech converts text into audio files. The node integrates with the FlowX Document Plugin for file storage and works in both standard and conversational workflows.
Speech to Text node configuration in Integration Designer

Transcribe audio

Convert audio recordings to text with language detection and confidence scores

Text to speech

Generate audio files from text with configurable voice, speed, and format

Multiple file sources

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

Chat integration

Automatically processes voice messages in conversational workflows

​
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

Select the operation and configure settings

Choose Transcribe or Text to Speech and configure the settings described below.

​
Operation

​
Operation
enum
required
The conversion direction.
OperationDescription
TranscribeConvert an audio file to text
Text to SpeechConvert text to an audio file
Default: Transcribe

​
Transcribe

Converts audio files into text. The node 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.

​
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
​
File Path
string
Path to the audio file in Document Plugin or S3 storage. Supports ${expression} placeholders for dynamic values.Only available when File Source is Document Plugin or S3 Protocol.Example: ${inputData.audioFilePath}

​
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

Toggle Use Test File to upload a sample audio file for testing the node without a live file source. Test files support the same audio formats listed above, with a maximum size of 15 MB.

​
Transcribe 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

​
Text to Speech

Converts text into an audio file. The generated audio is uploaded to the Document Plugin, and the node returns the file path and name.

​
TTS configuration

​
Text
string
required
The text to convert to speech. Supports ${expression} placeholders.Example: ${processData.responseMessage}
​
Voice
string
The voice to use for audio generation.Refer to your AI provider’s documentation for available voice options.
​
Model
string
The TTS model to use.Refer to your AI provider’s documentation for available models.
​
Response Format
string
The audio output format.Common formats: mp3, wav, aac, ogg
​
Speed
number
Playback speed multiplier for the generated audio.Range: 0.25 - 4.0Default: 1.0
​
Instructions
string
Additional instructions for the TTS model to control tone, style, or emphasis.

​
TTS output

The generated audio file is uploaded to the Document Plugin. The node writes the file reference under the configured Response Key: 
{
  "responseKey": {
    "audioFilePath": "/path/to/tts-output-abc123.mp3",
    "audioFileName": "tts-output-abc123.mp3"
  }
}
FieldTypeDescription
audioFilePathstringPath to the generated audio file in Document Plugin
audioFileNamestringGenerated file name

​
Response key

​
responseKey
string
required
The key where the node output is stored in the workflow data.Example: speechResult

​
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 operation completed and output is available under the response key
FailThe operation failed (unsupported format, file not found, service error)
Connect downstream nodes to the appropriate handle to manage both successful and failed transcription or TTS 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 April 9, 2026