You are helping me build the following AI agent workflow.

## Goal
Telegram Voice Email Assistant: Send voice messages to a Telegram bot to transcribe audio, retrieve recent emails, draft replies, or discuss threads hands-free.

## Specification
- What it does: Send a voice message to the bot to instantly transcribe your audio, fetch recent emails, draft replies, or discuss threads hands-free without typing. You get text responses or synthesized voice answers that automate your email management directly from Telegram using OpenAI and Gmail.
- Trigger: Triggered by an event (Manual · on voice message)
- Autonomy: You stay in control
- Expected setup effort: about an afternoon
- Tools/services involved:
  - Telegram: Voice input and response interface
  - OpenAI Chat Model: Transcription and conversational logic
  - Gmail: Retrieving, drafting, and sending emails

## Known pitfalls, handle each one explicitly in your implementation
1. Telegram has a strict message size limit so you must truncate long email summaries before sending them back to the user.
2. Ambiguous voice commands may lead to incorrect email actions, always ask the LLM to clarify intent before executing sensitive Gmail API calls.

## Reference implementation
https://n8n.io/workflows/9339 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/telegram-voice-email-assistant/ via usecasesforagents.com