Transform text into high-quality audio using advanced text-to-speech technology. Kelly AI offers 49 different voice models with various accents, languages, and speaking styles.
Generate speech
Convert text to speech using the text2voice() method.
Import and initialize
from kellyapi import KellyAPI
kelly = KellyAPI(api_key="your_api_key")
Generate audio
audio_data = await kelly.text2voice(
text="Hello, welcome to Kelly AI voice synthesis.",
model="en-US_LisaExpressive"
)
Save the audio
with open("output.mp3", "wb") as f:
f.write(audio_data)
Parameters
The text you want to convert to speech. Can include punctuation for natural pauses.
model
str
default:"en-US_LisaExpressive"
The voice model to use. Different models offer different accents, genders, and speaking styles.
Available voice models
Retrieve the complete list of 49 available voice models:
voices = await kelly.voice_models()
print(voices)
Complete example
import asyncio
from kellyapi import KellyAPI
async def generate_speech():
kelly = KellyAPI(api_key="your_api_key")
# List available voices
voices = await kelly.voice_models()
print("Available voices:", voices)
# Generate speech
text = "Artificial intelligence is transforming how we interact with technology."
audio_data = await kelly.text2voice(
text=text,
model="en-US_LisaExpressive"
)
# Save the audio file
with open("speech.mp3", "wb") as f:
f.write(audio_data)
print("Speech generated successfully!")
# Run the async function
asyncio.run(generate_speech())
Use cases
Audiobook creation
Convert written content to audio:
book_chapter = """
Chapter 1: The Beginning
It was a dark and stormy night when Sarah first discovered
the mysterious package on her doorstep.
"""
audio = await kelly.text2voice(
text=book_chapter,
model="en-US_LisaExpressive"
)
with open("chapter1.mp3", "wb") as f:
f.write(audio)
Voice notifications
Create audio alerts for applications:
audio = await kelly.text2voice(
text="Your order has been shipped and will arrive tomorrow.",
model="en-US_LisaExpressive"
)
with open("notification.mp3", "wb") as f:
f.write(audio)
Educational content
Generate pronunciation guides:
audio = await kelly.text2voice(
text="Welcome to today's lesson. We'll be learning about photosynthesis.",
model="en-US_LisaExpressive"
)
with open("lesson_intro.mp3", "wb") as f:
f.write(audio)
Accessibility features
Provide text-to-speech for visually impaired users:
webpage_text = "Welcome to our website. Navigate using the menu on the left."
audio = await kelly.text2voice(
text=webpage_text,
model="en-US_LisaExpressive"
)
with open("accessibility_audio.mp3", "wb") as f:
f.write(audio)
Multi-language content
Generate speech in different languages:
# English
audio_en = await kelly.text2voice(
text="Hello, how are you today?",
model="en-US_LisaExpressive"
)
# Save each language separately
with open("greeting_en.mp3", "wb") as f:
f.write(audio_en)
Batch processing
Generate multiple audio files:
import asyncio
from kellyapi import KellyAPI
async def batch_generate():
kelly = KellyAPI(api_key="your_api_key")
phrases = [
"Welcome to our service.",
"Your transaction is complete.",
"Thank you for your patience.",
"Please try again later."
]
for i, phrase in enumerate(phrases):
audio = await kelly.text2voice(
text=phrase,
model="en-US_LisaExpressive"
)
with open(f"audio_{i+1}.mp3", "wb") as f:
f.write(audio)
print(f"Generated audio_{i+1}.mp3")
asyncio.run(batch_generate())
The text2voice() method returns raw audio data as bytes. Save it to a file with an appropriate audio extension (.mp3, .wav, etc.).
Use punctuation in your text to control pacing and natural pauses. Commas create brief pauses, while periods create longer ones. Question marks add natural interrogative intonation.