TTS Python Quickstart Guide

1
from dotenv import load_dotenv
2
import os
3
from hume import AsyncHumeClient
4
import asyncio
5
from contextlib import contextmanager
6
from typing import Generator, Protocol
7
8
load_dotenv()
9
api_key = os.getenv("HUME_API_KEY")
10
if not api_key:
11
    raise EnvironmentError("HUME_API_KEY not found in environment variables")
12
13
hume = AsyncHumeClient(api_key=api_key)

1
import time
2
import base64
3
import tempfile
4
from pathlib import Path
5
import aiofiles
6
from hume.tts import ReturnGeneration
7
8
# Create an output directory in the temporary folder.
9
timestamp = int(time.time() * 1000)  # similar to Date.now() in JavaScript
10
output_dir = Path(tempfile.gettempdir()) / f"hume-audio-{timestamp}"
11
12
async def write_result_to_file(base64_encoded_audio: str, filename: str) -> None:
13
    file_path = output_dir / f"{filename}.wav"
14
    audio_data = base64.b64decode(base64_encoded_audio)
15
    async with aiofiles.open(file_path, "wb") as f:
16
        await f.write(audio_data)
17
    print("Wrote", file_path)
18
19
async def main() -> None:
20
    output_dir.mkdir(parents=True, exist_ok=True)
21
    print("Results will be written to", output_dir)
22
    
23
    # All the code examples in the remainder of the guide
24
    # belong within this main function.
25
26
if __name__ == "__main__":
27
    asyncio.run(main())
28
    print("Done")

1
from hume.tts import PostedUtterance
2
3
speech1 = await hume.tts.synthesize_json(
4
    utterances=[
5
        PostedUtterance(
6
            description="A refined, British aristocrat",
7
            text="Take an arrow from the quiver.",
8
        )
9
    ]
10
)
11
await write_result_to_file(speech1.generations[0].audio, "speech1_0")

1
generation_id = speech1.generations[0].generation_id
2
await hume.tts.voices.create(
3
    name=f"aristocrat-{int(time.time())}", 
4
    generation_id=generation_id
5
)

1
from hume.tts import PostedContextWithGenerationId, PostedUtteranceVoiceWithName, FormatPcm
2
3
speech2 = await hume.tts.synthesize_json(
4
    utterances=[
5
        PostedUtterance(
6
            voice=PostedUtteranceVoiceWithName(name="aristocrat"),
7
            text="Now take a bow.",
8
        )
9
    ],
10
    context=PostedContextWithGenerationId(generation_id=generation_id),
11
    num_generations=2,
12
)
13
14
await write_result_to_file(speech2.generations[0].audio, "speech2_0")
15
await write_result_to_file(speech2.generations[1].audio, "speech2_1")

1
speech3 = await hume.tts.synthesize_json(
2
    utterances=[
3
        PostedUtterance(
4
            voice=PostedUtteranceVoiceWithName(name="aristocrat"),
5
            description="Murmured softly, with a heavy dose of sarcasm and contempt",
6
            text="Does he even know how to use that thing?",
7
        )
8
    ],
9
    context=PostedContextWithGenerationId(
10
        generation_id=speech2.generations[0].generation_id
11
    ),
12
    num_generations=1,
13
)
14
await write_result_to_file(speech3.generations[0].audio, "speech3_0")

1
# Audio player setup for streaming playback
2
class AudioPlayer(Protocol):
3
    def send_audio(self, audio_bytes: bytes) -> None:
4
        pass
5
    def close(self) -> None:
6
        pass
7
8
class PyaudioPlayer(AudioPlayer):
9
    def __init__(self, stream):
10
        self.stream = stream
11
12
    def send_audio(self, audio_bytes: bytes) -> None:
13
        self.stream.write(audio_bytes)
14
15
    def close(self):
16
        self.stream.stop_stream()
17
        self.stream.close()
18
19
class DummyAudioPlayer(AudioPlayer):
20
    def send_audio(self, audio_bytes: bytes) -> None:
21
        print("Skipping playing back audio chunk...")
22
23
    def close(self) -> None:
24
        pass
25
26
@contextmanager
27
def get_audio_player() -> Generator[AudioPlayer]:
28
    try:
29
        import pyaudio
30
        audio = pyaudio.PyAudio()
31
        stream = audio.open(
32
            format=audio.get_format_from_width(2),
33
            channels=1,
34
            rate=48000,
35
            output=True,
36
        )
37
        yield PyaudioPlayer(stream)
38
    except ImportError:
39
        print("Skipping audio playback. Install pyaudio to enable playback.")
40
        yield DummyAudioPlayer()
41
42
# Streaming example with audio playback
43
print("Streaming audio...")
44
voice = PostedUtteranceVoiceWithName(name="aristocrat")
45
with get_audio_player() as player:
46
    async for snippet in hume.tts.synthesize_json_streaming(
47
        context=PostedContextWithGenerationId(
48
            generation_id=speech3.generations[0].generation_id,
49
        ),
50
        utterances=[
51
            PostedUtterance(text="He's drawn the bow...", voice=voice),
52
            PostedUtterance(text="he's fired the arrow...", voice=voice),
53
            PostedUtterance(text="I can't believe it! A perfect bullseye!", voice=voice)
54
        ],
55
        # Specify PCM format for direct audio playback
56
        format=FormatPcm(type="pcm"),
57
    ):
58
        player.send_audio(base64.b64decode(snippet.audio))