Python SDK for NeuralAudioAI. NeuralAudioAI is a gamechanger, introducing the new quality standards and prices of TTS services.
pip install neural_audio
-
NA_base (
na_base_v1)- Solid baseline, suits for most cases
- Support of 15 languages
- Real-time speed
-
NA_pro (
na_pro_v1)- Highest quality
- Best shot for PROs & Businesses
- Support of 52 languages
-
NA_vic (
na_vic) - comming soon...
from neural_audio import NeuralAudio
client = NeuralAudio(
api_key="YOUR_API_KEY",
)
client.text_to_speech.convert(
voice_id="32dcdovdplsmcos",
model_id="base_v1",
text="Hello world!",
)Hear the voice of the future
Test us! Want to see what we can? Visit the NeuralAudioAI to test our models, hear their voices or create your own!
Effortlessly recreate your voice with cutting-edge AI. Instantly generate a lifelike clone and explore the possibilities of voice transformation!
from neural_audio import NeuralAudio
client = NeuralAudio(
api_key="YOUR_API_KEY",
)
voice = client.clone_voice(
name="Alex",
description="A well-known male actor in his 50s, with a touch of excitement in his tone and a subtle sense of urgency in his delivery.",
sample="./sample_0.wav" # or ["./sample_0.wav", "./sample_1.mp3", "./sample_2.mkv"],
)Let your agents have real converstions with real-time audio streams. Both inside and out.
from neural_audio import NeuralAudio
streaming_client = NeuralAudio.streaming_client(
api_key="YOUR_API_KEY",
)
audio_stream = streaming_client.text_to_speech.convert(
text="Hi! How may I help you?",
voice="Adam",
model="na_pro_v1"
)
stream(audio_stream)Stream text chunks into audio as it's being generated, with <1s latency. Note: if chunks don't end with space or punctuation (" ", ".", "?", "!"), the stream will wait for more text.
from neural_audio import NeuralAudio
streaming_client = NeuralAudio.streaming_client(
api_key="YOUR_API_KEY",
)
def audio_stream():
with open("live_audio_input.wav", "rb") as audio:
while chunk := audio.read(4096):
yield chunk
audio_stream = streaming_client.conversation(
audio=audio_stream(),
voice="Adam",
llm="gpt-4o", # OPENAI_API_KEY required
model="na_pro_v1"
)
stream(audio_stream)