Speechmatics

Speechmatics provides real-time multilingual transcription for Vapi assistants. You can use Vapi’s managed integration or connect your own Speechmatics account in Integrations.

Speech-to-text

Set transcriber.provider to speechmatics. Speechmatics uses its default real-time model, so no model field is required.

$
curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \
>
  -H "Authorization: Bearer $VAPI_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "transcriber": { "provider": "speechmatics", "language": "en" }
>
  }'

For additional API configuration options, review the SpeechmaticsTranscriber fields in the Create Assistant API reference.

In the Vapi Dashboard, open an assistant’s Transcriber settings and select Speechmatics. Through the API, use the configuration below.

Supported languages

The following language values are currently accepted by Vapi for this provider.

Related