Need for an Automatic Arabic–English Bilingual Tra...
# support
a
I am building a bilingual AI agent in VAPI that speaks both Arabic and English. However, most transcribers in VAPI require selecting only one language. One multilingual transcriber is available, but it does not support Arabic. Using a single-language transcriber causes inaccurate results—English transcribers misinterpret Arabic, and Arabic transcribers misinterpret English. Therefore, I need a bilingual transcriber that can automatically switch between Arabic and English based on the spoken language. Is there anyone who can help me in this matter ? Thank You
v
Currently, VAPI's Deepgram transcriber supports Arabic transcription by setting the language to
'ar'
, but automatic switching between Arabic and English is not yet available. For best results, configure your assistant to use Deepgram's
'whisper'
model with Arabic as the language:
Copy code
json
"transcriber": {
  "provider": "Deepgram",
  "model": "whisper",
  "language": "ar"
}
If you need true bilingual auto-detection, you may need to monitor VAPI updates or consider a custom transcriber solution. Reference: [VAPI Changelog April 25, 2025](https://docs.vapi.ai/changelog/2025/4/25) Source: - [Changelog April 25, 2025](https://docs.vapi.ai/changelog/2025/4/25)
a
how to create a custom transcriber and how to connect with VAPI
c
Hi Abdullah, To create a custom transcriber and integrate it with Vapi, you can follow the steps outlined in the [Custom Transcriber Guide](https://docs.vapi.ai/customization/custom-transcriber). This process involves setting up a server to handle audio streaming from Vapi, forwarding it to your chosen transcription service, and returning transcripts back to Vapi. Here's a brief overview of how to implement this: 1. Set Up Your Server: - Create a new Node.js project and install necessary packages like
ws
,
express
,
dotenv
, and your transcriber’s SDK (e.g., Deepgram). 2. Configure the Environment: - Create a
.env
file with your transcriber’s API key and server port. 3. Create Transcription Service: - Implement a service in
transcriptionService.js
to handle the audio data and interact with your transcriber. 4. Set Up WebSocket Server: - Use
express
and
ws
to create a server that listens for connections from Vapi, processes audio, and returns transcription results. 5. Configure and Test: - Deploy and test your custom server. Expose it using a tool like ngrok for secure connection. For handling bilingual transcription (Arabic and English), Vapi currently lacks automatic switching capabilities. If this is crucial, you could develop a custom endpoint with logic to switch transcribers based on detected language segments. Monitoring updates on Vapi's capabilities or employing a solution like Vapi Squads, which allows using different assistants for different languages, might be beneficial. For comprehensive guidance on switching techniques, refer to [Vapi's documentation on multilingual support](https://docs.vapi.ai/customization/multilingual). Feel free to reach out if you have further questions on setting this up.