AI-Assisted Transcription and Summarisation of Parliamentary Meetings
Inform
What it collects
- Notices of parliamentary committee meetings from the House of Commons website (ourcommons.ca), including schedule and agenda metadata.
- Video recordings of parliamentary committee meetings from ParlVU (parlvu.parl.gc.ca), which are publicly available broadcasts. The register states no personal information is involved.
- Run by
- Innovation, Science and Economic Development Canada (ISED)
- Where
- No fixed location
- Kept
- Not stated by the Helpful Places.
- Shared with
- Accountable organization
- Your copy
- You cannot see the data it holds about you. What you can do
What it is for
ParlBrief is a Government of Canada tool that automatically transcribes audio recordings of bilingual parliamentary committee meetings, translates content between English and French, and produces structured summaries for departmental staff. It is currently in development and is used exclusively by Government of Canada employees — the public and members of Parliament are not direct users. The system processes publicly available recordings from parliamentary websites and does not involve personal information.
What it collects and what happens to it
Data taken in
- Notices of parliamentary committee meetings from the House of Commons website (ourcommons.ca), including schedule and agenda metadata.
- Video recordings of parliamentary committee meetings from ParlVU (parlvu.parl.gc.ca), which are publicly available broadcasts. The register states no personal information is involved.
Processing
- Speech-to-text models transcribe audio from bilingual parliamentary committee meeting recordings sourced from ParlVU (parlvu.parl.gc.ca).
- A combination of proprietary and open-source large language models perform machine translation between English and French, natural language generation of meeting summaries, and tone assessment.
What it does
- Converts audio recordings of bilingual parliamentary committee meetings into structured text transcriptions using speech-to-text models.
- Translates bilingual parliamentary content between English and French and assesses tone of meeting content using machine translation and natural language understanding models.
- Generates structured bilingual summaries of parliamentary committee meetings using natural language generation models; output is reviewed by GC employees before submission to the Privy Council Office.
Outputs
- Structured bilingual summaries and transcriptions of parliamentary committee meetings, delivered to GC employees and the Privy Council Office within three hours of meeting end.
- Tone assessments of parliamentary committee meeting content, produced as a structured signal alongside the meeting summary.
Run by
- Federal department responsible for deploying ParlBrief to automate transcription and summarisation of parliamentary committee meetings for its parliamentary affairs unit.
Built by
- The system was developed by the Government of Canada using a combination of proprietary and open-source language models. No third-party commercial vendor is identified as the primary builder in the register entry.
Kept for
Not stated by the Helpful Places.
Shared with
- ParlBrief outputs are intended for GC employees only. Members of the public do not have access to the summaries or transcriptions produced by the system.
- Summaries and transcriptions are available to GC employees, including parliamentary affairs staff and the Privy Council Office, as the designated primary users.
Stored
Not stated by the Helpful Places.
How to read the colours
Can it identify you?
- Anonymized data
- Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
- Pseudonymous data
- Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
- Identifiable data
- The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.
Who completes the loop?
- Human decides
- This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
- Human executes
- This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
- Autonomous
- This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.
Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.
- AI registerGovernment of Canada Algorithmic Impact Assessment Registry — ParlBrief (2526-ISED-ISDE-011)Innovation, Science and Economic Development Canada. AI Register entry 2526-ISED-ISDE-011.
- AI registerGovernment of Canada AI Register — ParlBrief
- AI registerGovernment of Canada AI Register — ParlBrief
- Register entryPublished by the Helpful Places. Reference ca58628b. This disclosure was drafted with AI assistance.Schema: ai@2026-05-06-beta
What you can do
Ask about this system
Questions go to the Helpful Places, not the vendor.
Your rights
- Right to Be Informed of AI UseGC employees are informed that AI is used in the production of parliamentary meeting summaries. The register confirms AI use is disclosed to users. For more information, contact Innovation, Science and Economic Development Canada.
- Right to Algorithmic TransparencyThe system is listed on the Government of Canada's public AI register with a description of its capabilities and data sources. GC employees can consult the register entry for information on how the system works.
Risks and safeguards
- Societal & cultural harmMachine translation errors or inaccurate tone assessments in bilingual parliamentary summaries could mislead departmental briefings or misrepresent committee proceedings.Safeguard: Output is reviewed by GC employees before submission; the system is described as automating rather than replacing human judgment. The bilingual design (English and French) addresses Canada's official languages obligations.