n8n-nodes-palatine-speech

Designed for seamless integration of Palatine Speech API into n8n workflows.

This is an n8n community node that integrates Palatine Speech into your workflows and enables audio processing capabilities such as transcription, diarization, sentiment analysis, and summarization.

Navigation

Supported Operations
Installation
Credentials
Workflow Example
Use Cases
Compatibility
Useful Resources
Keywords
License
Support

Looking for a Russian version? Here

Supported Operations

For details on each operation, see the Palatine Speech documentation.

• Full list of supported file types
• Full list of supported languages

Transcribe - speech transcription

Speech-to-Text (STT) converts audio/video into a written transcript.
It supports multiple languages and can automatically detect the language spoken in the recording.
It is well-suited for calls, interviews, lectures, and any other recordings where an accurate transcript is required.

Diarize - speaker diarization

Speaker diarization segments audio by speaker and labels speaker turns.
This is useful for meetings and interviews, where maintaining conversation structure matters.

Sentiment Analysis - sentiment analysis

Determines the emotional tone of speech in audio/video (and can also analyze text).
The result is a ranked list of sentiment classes with probabilities, where the first item is the most likely:
Very Negative, Negative, Neutral, Positive, Very Positive.

Summarize - audio summarization

Generates a structured summary from audio/video or pre-existing text.
In addition to built-in scenarios such as meeting_summary, it supports user_prompt, allowing you to define custom output structures (bullet points, decisions, action items, risks, Q&A, etc.).

Message to model - OpenAI-compatible chat

Generate a response from the Palatine Speech LLM using a list of messages (system, user, assistant).
You can select the model, tune generation parameters (temperature, max_tokens), and optionally enable thinking for deeper reasoning.

Supported response formats:

• Text
• JSON Object
• JSON Schema

Installation

1. In your n8n instance, go to Settings > Community Nodes -> Install
2. Enter: n8n-nodes-palatine-speech
3. Click Install

Make sure the environment variable N8N_COMMUNITY_PACKAGES_ENABLED=true is set.

Credentials

1. Go to Credentials -> + Create
2. Find Palatine Speech API
3. Fill in the fields:
   • API Key - available in your Palatine Speech dashboard
   • Base URL - default is https://api.palatine.ru

Workflow Example

1. Webhook -> Receive an audio file
2. Config -> Configure parameters
3. Palatine Speech -> Transcribe the file
4. Create record -> Create a table record
5. Telegram -> Send the result to a chat

Use Cases

• Meeting summaries
  Use Summarize (meeting_summary) to generate summaries, decisions, and action items grouped by owner and due date.
  Custom prompts can be used for additional structure.

• Lecture/webinar notes
  Recording -> Transcribe -> full transcript saved alongside materials.

• Automatic subtitles for video
  Extract audio -> Transcribe + Diarize -> convert to SRT/VTT.

• Customer support assistant
  Use Sentiment Analysis to determine tone and assign ticket priority.

• Action items extraction
  Use Message to model with JSON Schema to extract structured tasks (title, owner, due date, priority) and associated risks.
  Results can be sent to Jira / Notion / Asana or team chat.

Compatibility

Tested with n8n v1.39.1 and later.

Useful Resources

• Palatine Speech documentation
• n8n Community Nodes guide
• Official n8n GitHub

Keywords

n8n-community-node-package, n8n, palatine, speech-to-text, transcribe, transcription, stt, audio, ai, automation, voice-to-text, speech-recognition, audio-transcription, audio2text, audio-processing, diarization, speaker-diarization, speaker-segmentation, summarization, audio-summarization, sentiment-analysis, emotion-detection, tone-analysis, llm, chat-completions, openai-compatible, structured-output, json-schema

License

MIT

Support

Need help? Contact our Telegram support bot: @Speech_Palatine_Support_Bot