ElevenLabs

ElevenLabs is an AI-powered voice synthesis company specializing in ultra-realistic text-to-speech and voice cloning technology.

Categories: Artificial Intelligence

Type: elevenLabs/v1

Connections

Version: 1

API Key

Properties

Name	Label	Type	Description	Required
key	Key	STRING		true
value	API Key	STRING		true

Connection Setup

Find OAuth Client ID and Client Secret

Navigate to your dashboard.
Click on Developers.
Click on Create an API Key.
Click on Create Key.
Enable desired endpoints.
Click on Create Key.
Click on Copy to Clipboard.
Click on Close

Actions

Create Realtime Speech

Name: createRealtimeSpeech

Generate speech in real-time using ElevenLabs WebSocket-based text-to-speech API. Receives text via WebSocket, forwards to ElevenLabs for speech synthesis, and streams generated audio chunks back.

Properties

Name	Label	Type	Description	Required
voiceId	Voice	STRING	Voice to use for converting the text into speech.	true
model_id	Model	STRING Options eleven_flash_v2_5, eleven_multilingual_v2, eleven_turbo_v2_5, eleven_turbo_v2, eleven_monolingual_v1, eleven_multilingual_v1	The model to use for text-to-speech generation.	true
stability	Stability	NUMBER	Voice stability (0.0 to 1.0). Lower values produce more variation, higher values produce more consistent speech.	false
similarityBoost	Similarity Boost	NUMBER	Voice similarity boost (0.0 to 1.0). Higher values make the voice more closely match the original voice.	false
outputFormat	Output Format	STRING Options mp3_44100_128, mp3_44100_64, mp3_44100_32, pcm_16000, pcm_22050, pcm_24000, pcm_44100, ulaw_8000	The output audio format.	false

Example JSON Structure

{
  "label" : "Create Realtime Speech",
  "name" : "createRealtimeSpeech",
  "parameters" : {
    "voiceId" : "",
    "model_id" : "",
    "stability" : 0.0,
    "similarityBoost" : 0.0,
    "outputFormat" : ""
  },
  "type" : "elevenLabs/v1/createRealtimeSpeech"
}

Output

This action does not produce any output.

Create Realtime Transcript

Name: createRealtimeTranscript

Transcribe audio in real-time using ElevenLabs WebSocket-based speech-to-text API. Receives audio via WebSocket, forwards to ElevenLabs for transcription, and streams transcription results back.

Properties

Name	Label	Type	Description	Required
model_id	Model	STRING	The model to use for real-time transcription.	true
languageCode	Language Code	STRING	The language code for transcription (e.g., 'en' for English). If not specified, the language is auto-detected.	false
sampleRate	Sample Rate	INTEGER	The sample rate of the audio in Hz.	false
audioFormat	Audio Format	STRING Options pcm_16000, pcm_22050, pcm_44100, ulaw_8000	The format of the audio data.	false
includeTimestamps	Include Timestamps	BOOLEAN Options true, false	Whether to include word-level timestamps in the transcription.	false

Example JSON Structure

{
  "label" : "Create Realtime Transcript",
  "name" : "createRealtimeTranscript",
  "parameters" : {
    "model_id" : "",
    "languageCode" : "",
    "sampleRate" : 1,
    "audioFormat" : "",
    "includeTimestamps" : false
  },
  "type" : "elevenLabs/v1/createRealtimeTranscript"
}

Name	Label	Type	Description	Required
text	Text	STRING	The text that will get converted into a sound effect.	true

Example JSON Structure

{
  "label" : "Create Sound Effect",
  "name" : "createSoundEffect",
  "parameters" : {
    "text" : ""
  },
  "type" : "elevenLabs/v1/createSoundEffect"
}

Output

Type: FILE_ENTRY

Properties

Name	Type	Description
extension	STRING
mimeType	STRING
name	STRING
url	STRING

Output Example

{
  "extension" : "",
  "mimeType" : "",
  "name" : "",
  "url" : ""
}

Create Speech

Name: createSpeech

Converts text into speech using a voice of your choice and returns audio.

Properties

Name	Label	Type	Description	Required
voiceId	Voice	STRING	Voice you want to use for converting the text into speech.	true
text	Text	STRING	Text you want to convert into speech.	true

Example JSON Structure

{
  "label" : "Create Speech",
  "name" : "createSpeech",
  "parameters" : {
    "voiceId" : "",
    "text" : ""
  },
  "type" : "elevenLabs/v1/createSpeech"
}

Output

Type: FILE_ENTRY

Properties

Name	Type	Description
extension	STRING
mimeType	STRING
name	STRING
url	STRING

Output Example

{
  "extension" : "",
  "mimeType" : "",
  "name" : "",
  "url" : ""
}

Create Speech With Timing

Name: createSpeechWithTiming

Generate speech from text with precise character-level timing information for audio-text synchronization.

Properties

Name	Label	Type	Description	Required
voiceId	Voice	STRING	Voice you want to use for converting the text into speech.	true
text	Text	STRING	Text you want to convert into speech.	true

Example JSON Structure

{
  "label" : "Create Speech With Timing",
  "name" : "createSpeechWithTiming",
  "parameters" : {
    "voiceId" : "",
    "text" : ""
  },
  "type" : "elevenLabs/v1/createSpeechWithTiming"
}

Output

Type: OBJECT

Properties

Name	Type	Description
audio_base64	STRING	Base64 encoded audio data
alignment	OBJECT Properties {[STRING](characters), [NUMBER](character_start_times_seconds), [NUMBER](character_end_times_seconds)}
normalized_alignment	OBJECT Properties {[STRING](characters), [NUMBER](character_start_times_seconds), [NUMBER](character_end_times_seconds)}

Output Example

{
  "audio_base64" : "",
  "alignment" : {
    "characters" : [ "" ],
    "character_start_times_seconds" : [ 0.0 ],
    "character_end_times_seconds" : [ 0.0 ]
  },
  "normalized_alignment" : {
    "characters" : [ "" ],
    "character_start_times_seconds" : [ 0.0 ],
    "character_end_times_seconds" : [ 0.0 ]
  }
}

Create Transcript

Name: createTranscript

Transcribe an audio or video file.

Properties

Name	Label	Type	Description	Required
model_id	Model	STRING	The ID of the model to use for transcription, currently only ‘scribe_v1’ is available.	true
file	File Entry	FILE_ENTRY	The file object with content to transcribe. All major audio and video formats are supported. The file size must be less than 1GB.	true

Example JSON Structure

{
  "label" : "Create Transcript",
  "name" : "createTranscript",
  "parameters" : {
    "model_id" : "",
    "file" : {
      "extension" : "",
      "mimeType" : "",
      "name" : "",
      "url" : ""
    }
  },
  "type" : "elevenLabs/v1/createTranscript"
}

Output

Type: OBJECT

Properties

Name	Type	Description
language_code	STRING	The detected language code (e.g. ‘eng’ for English).
language_probability	NUMBER	The confidence score of the language detection (0 to 1).
text	STRING	The raw text of the transcription.
words	ARRAY Items [{STRING(text), NUMBER(start), NUMBER(end), STRING(type)}]	List of words with their timing information.

Output Example

{
  "language_code" : "",
  "language_probability" : 0.0,
  "text" : "",
  "words" : [ {
    "text" : "",
    "start" : 0.0,
    "end" : 0.0,
    "type" : ""
  } ]
}

On this page