🎙️ Triage Voice Notes with the Vercel AI SDK and ZeroGPU

import { zerogpu } from '@zerogpu/ai-sdk-provider';
import { generateSpeech } from 'ai';
import { writeFile } from 'node:fs/promises';

const voicemail =
  "Hi, this is Dana Whitfield from Brightline Dental. Our online booking page has been down since this morning " +
  "and patients can't schedule appointments. We're on the Pro plan, account number 48213. " +
  'Please call me back at 555-0142 as soon as you can. Thanks.';

const { audio } = await generateSpeech({
  model: zerogpu.speech('chatterbox-nano'),
  text: voicemail,
  voice: 'nova',
});

await writeFile('voicemail.mp3', audio.uint8Array);
console.log(`Saved voicemail.mp3 (${audio.mediaType}, ${audio.uint8Array.length.toLocaleString()} bytes)`);

import { zerogpu } from '@zerogpu/ai-sdk-provider';
import { generateSpeech, generateText, Output, transcribe } from 'ai';
import { readFile, writeFile } from 'node:fs/promises';
import { z } from 'zod';

const transcript = await transcribe({
  model: zerogpu.transcription('whisper-tiny'),
  audio: await readFile('voicemail.mp3'),
  providerOptions: { zerogpu: { language: 'en' } },
});

console.log(transcript.text);
console.log(
  `\nlanguage: ${transcript.language}, duration: ${transcript.durationInSeconds}s, segments: ${transcript.segments.length}`,
);

const ticketSchema = z.object({
  summary: z.string().describe('One sentence describing what the caller needs'),
  intent: z.enum(['outage', 'billing', 'how_to', 'feature_request', 'other']),
  priority: z.enum(['low', 'normal', 'high', 'urgent']),
  caller: z.object({
    name: z.string(),
    company: z.string().nullable(),
    phone: z.string().nullable(),
    accountNumber: z.string().nullable(),
  }),
  actionItems: z.array(z.string()),
});

const { output: ticket, usage } = await generateText({
  model: zerogpu('gpt-6-luna'),
  output: Output.object({ schema: ticketSchema }),
  instructions:
    'You triage voicemails for a SaaS support desk. Anything that stops customers from using the product is urgent.',
  prompt: `Voicemail transcript:\n\n${transcript.text}`,
});

console.log(JSON.stringify(ticket, null, 2));
console.log(`tokens: ${usage.inputTokens} in / ${usage.outputTokens} out`);

const firstName = ticket.caller.name.split(' ')[0];
const reply =
  `Hi ${firstName}, thanks for your message. We've logged this as ${ticket.priority} priority ` +
  'and an engineer will call you back shortly.';

const { audio } = await generateSpeech({
  model: zerogpu.speech('chatterbox-nano'),
  text: reply,
  voice: 'alloy',
});

await writeFile('reply.mp3', audio.uint8Array);
console.log(reply);
console.log(`Saved reply.mp3 (${audio.uint8Array.length.toLocaleString()} bytes)`);