Voice bug report

Tell Telegram about a bug — get a formatted report and a Jira task.

Voice & meetings · Test automation & QA

Repository on GitHub (GitHub)

Result

Generate a bug report in 60 seconds

About the project

The solution turns a tester's voice notes into structured bug reports in English. Instead of filling in forms during testing, it is enough to send the bot a voice message describing the problem.

AI recognizes the speech, extracts the data about the bug and builds a report from a template. A second AI agent checks the prepared result. The system saves the data to Google Sheets, creates a formatted document in Google Docs and a task in Jira, and sends a confirmation to Telegram.

This way a problem can be recorded right after it is found, without postponing its description and without moving the same data by hand between tools.

How it works

  1. Voice message in Telegram
  2. Speech recognition
  3. Creating and AI-checking the bug report
  4. An entry in the table, a document and a task in Jira

Features

  • Recognition of the voice description of a bug.

  • Turning a free-form account into a standardized bug report in English.

  • An additional check of the report by a separate AI agent.

  • Maintaining a summary table of bugs in Google Sheets.

  • Creating a formatted report in Google Docs and a task in Jira.

  • Confirmation of processing in Telegram.

Where it can be used

  • QA teams — recording bugs right during testing.
  • Development teams — a single format for describing problems and passing them to Jira.
  • Technical support and internal services — the approach can be adapted to turn voice requests into structured tickets.

Technologies

  • Telegram
  • n8n
  • OpenAI
  • Google Sheets
  • Google Docs
  • Jira

More projects

All projects

Test automation & QA · AI evaluation & model selection

QA LLM Lab

Check answer quality and resistance to provocative requests — without running conversations by hand.

Automatic checks of AI chatbots in Telegram: functional tests, AI evaluation of answers and security checks.

  • Promptfoo
  • NVIDIA Garak
  • Python
  • Telethon
  • Telegram
  • +2

Process automation & integrations · Test automation & QA

AI bug summary from Jira to Google Sheets

The team works in Jira — managers get a clear summary without manual data transfer.

An automatic bug summary for QA, managers and other teams instead of shortening tickets by hand.

Result Manual data transfer when preparing the summary has been eliminated

  • n8n
  • OpenAI
  • Jira
  • Google Sheets

Voice & meetings · Documents

Local transcription of large audio files

Hours of recordings turned into ready text — without cloud service limits.

Batch transcription of audio recordings on your own computer with GPU acceleration, fully offline.

Result About 60 hours of lectures processed in about 5 hours on a GPU

  • Python
  • Faster Whisper
  • NVIDIA CUDA
  • FFmpeg
  • n8n
  • +2

Start with one process.

Describe what is currently done manually, what data is involved and what result you would like to achieve. You do not need a technical specification or a chosen model to begin.

Fill in the brief
AI bot consultation (opens Telegram, an external service)

Please do not share trade secrets, source code, or sensitive personal data before an NDA (non-disclosure agreement) is signed.