TTS TypeScript Quickstart Guide

1
import { HumeClient } from "hume"
2
import dotenv from "dotenv"
3
4
dotenv.config()
5
6
const hume = new HumeClient({ 
7
  apiKey: process.env.HUME_API_KEY!
8
})

1
import fs from "fs/promises"
2
import path from "path"
3
import * as os from "os"
4
import * as child_process from "child_process"
5
6
const outputDir = path.join(os.tmpdir(), `hume-audio-${Date.now()}`)
7
8
const writeResultToFile = async (base64EncodedAudio: string, filename: string) => {
9
  const filePath = path.join(outputDir, `${filename}.wav`)
10
  await fs.writeFile(filePath, Buffer.from(base64EncodedAudio, "base64"))
11
  console.log('Wrote', filePath)
12
}
13
14
const startAudioPlayer = () => {
15
  const proc = child_process.spawn('ffplay', ['-nodisp', '-autoexit', '-infbuf', '-i', '-'], {
16
    detached: true,
17
    stdio: ['pipe', 'ignore', 'ignore'],
18
  })
19
20
  proc.on('error', (err) => {
21
    if ((err as any).code === 'ENOENT') {
22
      console.error('ffplay not found. Please install ffmpeg to play audio.')
23
    }
24
  })
25
26
  return {
27
    sendAudio: (audio: string) => {
28
      const buffer = Buffer.from(audio, "base64")
29
      proc.stdin.write(buffer)
30
    },
31
    stop: () => {
32
      proc.stdin.end()
33
      proc.unref()
34
    }
35
  }
36
}
37
38
const main = async () => {
39
  await fs.mkdir(outputDir)
40
  console.log('Writing to', outputDir)
41
  
42
  // All the code examples in the remainder of the guide
43
  // belong within this main function.
44
}
45
46
main().then(() => console.log('Done')).catch(console.error)

1
const speech1 = await hume.tts.synthesizeJson({
2
  utterances: [{
3
    description: "A refined, British aristocrat",
4
    text: "Take an arrow from the quiver."
5
  }]
6
})
7
await writeResultToFile(speech1.generations[0].audio, "speech1_0")

1
await hume.tts.voices.create({
2
  name: `aristocrat-${Date.now()}`,
3
  generationId: speech1.generations[0].generationId,
4
})

1
const speech2 = await hume.tts.synthesizeJson({
2
  utterances: [{
3
    voice: { name: "aristocrat" },
4
    text: "Now take a bow."
5
  }],
6
  context: {
7
    generationId: speech1.generations[0].generationId
8
  },
9
  numGenerations: 2,
10
})
11
await writeResultToFile(speech2.generations[0].audio, "speech2_0")
12
await writeResultToFile(speech2.generations[1].audio, "speech2_1")

1
const speech3 = await hume.tts.synthesizeJson({
2
  utterances: [{
3
    voice: { name: "aristocrat" },
4
    description: "Murmured softly, with a heavy dose of sarcasm and contempt",
5
    text: "Does he even know how to use that thing?"
6
  }],
7
  context: {
8
    generationId: speech2.generations[0].generationId
9
  },
10
  numGenerations: 1
11
})
12
await writeResultToFile(speech3.generations[0].audio, "speech3_0")

1
const voice = { name: "aristocrat" }
2
const audioPlayer = startAudioPlayer()
3
for await (const snippet of await hume.tts.synthesizeJsonStreaming({
4
  context: {
5
    generationId: speech3.generations[0].generationId,
6
  },
7
  utterances: [{ voice, text: "He's drawn the bow..." }, { voice, text: "he's fired the arrow..." }, { voice, text: "I can't believe it! A perfect bullseye!" }],
8
9
  stripHeaders: true
10
})) {
11
  audioPlayer.sendAudio(snippet.audio)
12
}
13
audioPlayer.stop()