How to Record and Transcribe Meetings with Speechmatics

Speechmatics built its reputation on accuracy across accents and dialects — the meetings where a single language label doesn't survive first contact with an international team. Like every speech-to-text API, though, it starts from an audio file. Getting the meeting into a file is your problem.

A meeting bot makes that problem one POST request. This guide routes Zoom, Google Meet and Microsoft Teams calls through your Speechmatics account.

Step 1: Get your keys

• Speechmatics: create an API key in the Speechmatics portal.
• Meeting BaaS: self-serve signup at auth.meetingbaas.com — first 8 recording hours free.

Step 2: Send a bot with Speechmatics configured

curl -X POST "https://api.meetingbaas.com/v2/bots" \
     -H "Content-Type: application/json" \
     -H "x-meeting-baas-api-key: $API_KEY" \
     -d '{
           "meeting_url": "https://teams.microsoft.com/l/meetup-join/...",
           "bot_name": "Speechmatics Bot",
           "transcription_config": {
             "provider": "speechmatics",
             "api_key": "'"$SPEECHMATICS_API_KEY"'",
             "custom_params": {
               "language": "en",
               "model": "enhanced",
               "diarization": "speaker"
             }
           }
         }'

custom_params maps to Speechmatics' own configuration: language, the enhanced model for maximum accuracy, and diarization: "speaker" for who-said-what. Region-specific deployments are covered by the region field on transcription_config.

Step 3: Receive Speechmatics-native output

Your webhook receives the transcription artifact in Speechmatics' native response structure, plus the recording, participant join/leave events and the bot's own speaker timeline in the standard Meeting BaaS format. If you're migrating from uploading files to the Speechmatics batch API, the output parsing you already have carries over.

Why this combination

• Accent and dialect robustness: meetings are exactly the audio Speechmatics is strongest on — cross-border calls with mixed accents.
• Compliance chains: Meeting BaaS supports on-premises deployment; combined with Speechmatics' deployment options, regulated teams can keep audio inside their perimeter.
• Your billing: Speechmatics usage runs on your account; Meeting BaaS adds 0.05 tokens per recorded hour for bring-your-own-key transcription (Pro plans and above) on top of the 1 token per hour recording rate.

Next steps

• Speechmatics meeting transcription — the integration page
• All transcription providers
• On-premises deployment
• API documentation