TTS Python Quickstart Guide

1
# app.py
2
import os
3
from hume import AsyncHumeClient
4
from dotenv import load_dotenv
5
6
load_dotenv()
7
8
api_key = os.getenv("HUME_API_KEY")
9
if not api_key:
10
    raise EnvironmentError("HUME_API_KEY not found in environment variables.")
11
12
hume = AsyncHumeClient(api_key=api_key)

1
import base64
2
from hume.empathic_voice.chat.audio.audio_utilities import play_audio_streaming
3
from hume.tts import PostedUtterance, PostedUtteranceVoiceWithName
4
5
utterance = PostedUtterance(
6
    text="Dogs became domesticated between 23,000 and 30,000 years ago.",
7
    voice=PostedUtteranceVoiceWithName(name='Ava Song', provider='HUME_AI')
8
)
9
10
stream = hume.tts.synthesize_json_streaming(
11
    utterances=[utterance],
12
    strip_headers=True,
13
    version="1"
14
)
15
16
await play_audio_streaming(base64.b64decode(chunk.audio) async for chunk in stream)

1
import base64
2
import time
3
from hume.empathic_voice.chat.audio.audio_utilities import play_audio
4
from hume.tts import PostedUtterance
5
6
result1 = await hume.tts.synthesize_json(
7
    utterances=[PostedUtterance(
8
        description="Crisp, upper-class British accent with impeccably articulated consonants and perfectly placed vowels. Authoritative and theatrical, as if giving a lecture.",
9
        text="The science of speech. That\'s my profession; also my hobby. Happy is the man who can make a living by his hobby!"
10
    )],
11
    num_generations=2,
12
)
13
14
sample_number = 1
15
for generation in result1.generations:
16
    print(f'Playing option {sample_number}... সন')
17
    audio_data = base64.b64decode(generation.audio)
18
    await play_audio(audio_data)
19
    sample_number += 1
20
21
# Prompt user to select which voice they prefer
22
print('\nWhich voice did you prefer?')
23
print('1. First voice (generation ID:', result1.generations[0].generation_id, ') সন')
24
print('2. Second voice (generation ID:', result1.generations[1].generation_id, ') সন')
25
26
try:
27
    user_choice = input('Enter your choice (1 or 2): ').strip()
28
except EOFError:
29
    user_choice = '1'
30
    print('No input available, selecting option 1')
31
32
selected_index = int(user_choice) - 1
33
34
if selected_index not in [0, 1]:
35
    raise ValueError('Invalid choice. Please select 1 or 2.')
36
37
selected_generation_id = result1.generations[selected_index].generation_id
38
print(f'Selected voice option {selected_index + 1} (generation ID: {selected_generation_id})')
39
40
# Save the selected voice
41
voice_name = f'higgins-{int(time.time() * 1000)}'
42
await hume.tts.voices.create(
43
    name=voice_name,
44
    generation_id=selected_generation_id,
45
)
46
47
print(f'Created voice: {voice_name}')

1
import base64
2
from hume.empathic_voice.chat.audio.audio_utilities import play_audio_streaming
3
from hume.tts import PostedUtterance, PostedUtteranceVoiceWithName, PostedContextWithGenerationId
4
5
stream = hume.tts.synthesize_json_streaming(
6
    utterances=[PostedUtterance(
7
        voice=PostedUtteranceVoiceWithName(name=voice_name),
8
        text="YOU can spot an Irishman or a Yorkshireman by his brogue. I can place any man within six miles. I can place him within two miles in London. Sometimes within two streets.",
9
        description="Bragging about his abilities"
10
    )],
11
    context=PostedContextWithGenerationId(
12
        generation_id=selected_generation_id
13
    ),
14
    strip_headers=True
15
)
16
17
await play_audio_streaming(base64.b64decode(chunk.audio) async for chunk in stream)

1
import asyncio
2
import base64
3
from streaming import StreamingTtsClient
4
from hume.tts import PublishTts
5
from hume.empathic_voice.chat.audio.audio_utilities import play_audio_streaming
6
7
stream = await StreamingTtsClient.connect(api_key)
8
9
# Helper functions for flushing and closing the stream
10
def send_flush():
11
    asyncio.create_task(stream._send_dict({"flush": True}))
12
13
def send_close():
14
    asyncio.create_task(stream._send_dict({"close": True}))
15
16
async def send_input():
17
    print("Sending TTS messages...")
18
    stream.send(PublishTts(text="Hello world."))
19
    send_flush()
20
    print('Waiting 8 seconds...')
21
    await asyncio.sleep(8)
22
    stream.send(PublishTts(text="Goodbye, world."))
23
    send_flush()
24
    print("Closing stream...")
25
    send_close()
26
27
async def handle_messages():
28
    await play_audio_streaming(base64.b64decode(chunk.audio) async for chunk in stream)
29
30
await asyncio.gather(handle_messages(), send_input())