@AiTitus :) Absolutely! VAPI is designed to be flexible and modular, allowing you to integrate your own custom models, including a custom speech-to-text API. You can simply plug in your API into the VAPI ecosystem. If you need any assistance with the integration process or have specific questions about compatibility or setup, please feel free to ask.

Got it. Tagging @User for additional help.

[docs] https://dump.sahilsuman.me/emb5bcy8.py https://dump.sahilsuman.me/h4lfncbn.md [example] You can integrate any transcriber, via the CustomTranscriber option. For more information, please visit https://api.vapi.ai/api and search for the CustomTranscriber Schema. Rough example to handle the CustomTranscriber data. const WebSocket = require('ws'); const http = require('http'); const server = http.createServer(app); const wss = new WebSocket.Server({ server }); wss.on('connection', (ws) => { console.log('WebSocket client connected'); ws.on('message', (message, isBinary) => { if (isBinary) { console.log('Received binary message', message.length, 'bytes'); } else { console.log('Received text message:', JSON.parse(message)); } }); ws.on('close', () => { clearInterval(intervalId); console.log('WebSocket client disconnected'); }); // Send a transcription response every 5 seconds const intervalId = setInterval(() => { if (ws.readyState === WebSocket.OPEN) { const message = { type: 'transcriber-response', transcription: 'hey', channel: 'customer', }; ws.send(JSON.stringify(message)); console.log('Sent transcription response:', message); } }, 5000); });

Do let me know how it goes.

Because of no response closing this ticket.