AI Trainer: Telegram Message Send¶

This workflow delivers AI-generated content to Telegram users with intelligent format selection — sending either voice messages (using ElevenLabs or OpenAI text-to-speech) or plain text based on user preferences. It serves as a delivery endpoint for AI training systems that need to communicate with learners through Telegram.

Purpose¶

No business context provided yet — add a context.md to enrich this documentation.

This workflow appears to be part of an AI training or coaching system that delivers personalized content to users via Telegram. It intelligently chooses between voice and text delivery based on user preferences, making learning content more accessible and engaging.

How It Works¶

Receives Input: Another workflow triggers this one with message content, voice preference, and target chat ID
Format Decision: Checks if the user wants voice output or text-only delivery
Voice Generation (if requested):
- Sets up ElevenLabs voice ID for text-to-speech conversion
- Attempts to generate audio using ElevenLabs API
- Falls back to OpenAI's text-to-speech if ElevenLabs fails
Message Delivery: Sends either the generated audio file or plain text to the specified Telegram chat
Confirmation: Returns success status to the calling workflow

Workflow Diagram¶

graph TD
    A[When Executed by Another Workflow] --> B[If Voice Out]
    B -->|Voice Requested| C[Voice ID]
    B -->|Text Only| G[Telegram1 - Send Text]
    C --> D[Generate voice 11labs]
    D -->|Success| E[Telegram - Send Audio]
    D -->|Error| F[Generate voice openai backup]
    F --> E
    E --> H[Output]
    G --> H

Trigger¶

Execute Workflow Trigger: This workflow is designed to be called by other workflows, not triggered directly. It expects three input parameters: - output (string): The message content to send - is_voice (boolean): Whether to send as voice message or text - chat_id (string): The Telegram chat ID to send the message to

Nodes Used¶

Node Type	Node Name	Purpose
Execute Workflow Trigger	When Executed by Another Workflow	Receives input from calling workflow
If	If Voice Out	Determines delivery format based on user preference
Set	Voice ID	Configures ElevenLabs voice ID for audio generation
HTTP Request	Generate voice 11labs	Converts text to speech using ElevenLabs API
OpenAI	Generate voice openai (backup)	Backup text-to-speech service
Telegram	Telegram	Sends audio messages to Telegram chat
Telegram	Telegram1	Sends text messages to Telegram chat
Set	Output	Returns execution status to calling workflow

External Services & Credentials Required¶

ElevenLabs API¶

Credential: Elevenlabs (Johns Key) (HTTP Header Auth)
Purpose: Primary text-to-speech service
Required: API key for ElevenLabs service

OpenAI API¶

Credential: OpenAi account
Purpose: Backup text-to-speech service
Required: OpenAI API key with audio generation access

Telegram Bot API¶

Credential: Telegram account 2
Purpose: Message delivery to Telegram chats
Required: Telegram bot token

Environment Variables¶

No environment variables are used in this workflow. All configuration is handled through n8n credentials and hardcoded values.

Data Flow¶

Input¶

{
  "output": "Message content to send",
  "is_voice": true/false,
  "chat_id": "Telegram chat ID"
}

Output¶

{
  "ok": true/false
}

The workflow returns a boolean indicating successful message delivery.

Error Handling¶

ElevenLabs Fallback: If ElevenLabs voice generation fails, the workflow automatically falls back to OpenAI's text-to-speech service
Continue on Error: The ElevenLabs node is configured to continue execution even if it encounters errors, ensuring the backup system activates

Known Limitations¶

Voice ID is hardcoded (Z8dg0fyk7p6js7cQ7lgi) and cannot be dynamically changed per user
No retry mechanism if both voice generation services fail
No validation of input parameters before processing
Audio files are always named "audio.mp3" regardless of content

This workflow is designed to be called by other AI training workflows that generate content and need to deliver it to users. Look for workflows that use "Execute Workflow" nodes targeting this workflow.

Setup Instructions¶

Import Workflow: Import the JSON into your n8n instance
Configure Credentials:
- Set up ElevenLabs HTTP Header Auth credential with your API key
- Configure OpenAI API credential for backup voice generation
- Add Telegram Bot API credential with your bot token
Test Voice Generation:
- Verify ElevenLabs API access and voice ID validity
- Test OpenAI text-to-speech as backup option
Telegram Setup:
- Ensure your Telegram bot has permission to send messages and audio files
- Test with a known chat ID to verify delivery
Integration:
- Update calling workflows to use this workflow's ID
- Ensure input parameters match the expected format
Customize Voice:
- Replace the hardcoded voice ID in the "Voice ID" node with your preferred ElevenLabs voice
- Adjust voice settings (stability, similarity_boost) as needed