createTranscriber.ts

import { RealtimeTranscriber, RealtimeTranscript } from 'assemblyai';
import { getAssemblyToken } from './getAssemblyToken';

export async function createTranscriber(
  transcriptionProcessed: (transcription: string, isFinal: boolean) => void
): Promise<RealtimeTranscriber | undefined> {
  const token = await getAssemblyToken();

  if (!token) {
    console.error('No token found');

    return;
  }

  const transcriber = new RealtimeTranscriber({
    sampleRate: 16_000,
    token: token,
    wordBoost: ['Llama'],
    endUtteranceSilenceThreshold: 1000,
    // encoding: 'pcm_mulaw',
  });

  transcriber.on('open', ({ sessionId }) => {
    console.log(`Transcriber opened with session ID: ${sessionId}`);
  });

  transcriber.on('error', (error: Error) => {
    console.error('Transcriber error:', error);
    await transcriber.close();
  });

  transcriber.on('close', (code: number, reason: string) => {
    console.log(`Transcriber closed with code ${code} and reason: ${reason}`);
    transcriber = null;
  });

  transcriber.on('transcript', (transcript: RealtimeTranscript) => {
    if (!transcript.text) {
      return;
    }

    if (transcript.message_type === 'PartialTranscript') {
      transcriptionProcessed(transcript.text, false);
    } else {
      transcriptionProcessed(transcript.text, true);
    }
  });

  return transcriber;
}

createTranscriber2.ts

import { RealtimeTranscriber, RealtimeTranscript } from 'assemblyai';
import { getAssemblyToken } from './getAssemblyToken';
import { Dispatch, SetStateAction } from 'react';

export async function createTranscriber(
  transcriptionProcessed: (transcription: string, isFinal: boolean) => void,
  setLlamaActive: Dispatch<SetStateAction<boolean>>,
  processPrompt: (prompt: string) => void
): Promise<RealtimeTranscriber | undefined> {
  const token = await getAssemblyToken();
  
  if (!token) {
    console.error('No token found');
    return;
  }
  const transcriber = new RealtimeTranscriber({
    sampleRate: 16_000,
    token: token,
    wordBoost: ['Llama'],
    endUtteranceSilenceThreshold: 1000,
    //   encoding: 'pcm_mulaw',
  });

  transcriber.on('open', ({ sessionId }) => {
    console.log(`Transcriber opened with session ID: ${sessionId}`);
  });

  transcriber.on('error', (error: Error) => {
    console.error('Transcriber error:', error);
    await transcriber.close();
  });

  transcriber.on('close', (code: number, reason: string) => {
    console.log(`Transcriber closed with code ${code} and reason: ${reason}`);
    transcriber = null;
  });

  transcriber.on('transcript', (transcript: RealtimeTranscript) => {
    if (!transcript.text) {
      return;
    }

    // Detect if we're asking something for the LLM
    setLlamaActive(transcript.text.toLowerCase().indexOf('llama') > 0);

    if (transcript.message_type === 'PartialTranscript') {
      transcriptionProcessed(transcript.text, false);
    } else {
      transcriptionProcessed(transcript.text, true);

      if (transcript.text.toLowerCase().indexOf('llama') > 0) {
        processPrompt(transcript.text);
      }
    }
  });

  return transcriber;
}

route.ts

import { AssemblyAI } from 'assemblyai';

export async function POST(request: Request) {
  const apiKey = process.env.ASSEMBLY_API_KEY;
  if (!apiKey) {
    return Response.error();
  }

  const client = new AssemblyAI({ apiKey: apiKey });
  const body = await request.json();

  const prompt = body?.prompt;

  if (!prompt) {
    return Response.error();
  }

  console.log('This is the prompt: ', prompt);

  const finalPrompt = `You act as an assistant during a video call. You get a question and I want you to answer it directly without repeating it.
  If you do not know the answer, clearly state that.
  Here is the user question:
  ${prompt}`;

  const lemurResponse = await client.lemur.task({
    prompt: finalPrompt,
  });

  const response = {
    prompt: prompt,
    response: lemurResponse.response,
  };

  return Response.json(response);
}