How to stream LLM to TTS in Realtime

1
import asyncio
2
import websockets
3
from groq import Groq
4
from smallestai.waves import WavesClient, TextToAudioStream  
5
6
# Initialize Groq (LLM) and Smallest (TTS) instances
7
llm = Groq(api_key="GROQ_API_KEY")
8
tts = WavesClient(api_key="SMALLEST_API_KEY")
9
WEBSOCKET_URL = "wss://echo.websocket.events" # Mock WebSocket server
10
11
# Async function to stream text generation from LLM
12
async def generate_text(prompt):
13
    completion = llm.chat.completions.create(
14
        messages=[{"role": "user", "content": prompt}],
15
        model="llama3-8b-8192",
16
        stream=True,
17
    )
18
19
    # Yield text as it is generated
20
    for chunk in completion:
21
        text = chunk.choices[0].delta.content
22
        if text:
23
            yield text
24
25
# Main function to run the process
26
async def main():
27
    # Initialize the TTS processor
28
    processor = TextToAudioStream(tts_instance=tts)
29
30
    # Generate text from LLM
31
    llm_output = generate_text("Explain text to speech like I am five in 5 sentences.")
32
33
    # Stream the generated speech throught a websocket
34
    async with websockets.connect(WEBSOCKET_URL) as ws:
35
        print("Connected to WebSocket server.")
36
37
        # Stream the generated speech
38
        async for audio_chunk in processor.process(llm_output):
39
            await ws.send(audio_chunk)  # Send audio chunk
40
            echoed_data = await ws.recv()  # Receive the echoed message
41
            print("Received from server:", echoed_data[:20], "...")  # Print first 20 bytes
42
43
        print("WebSocket connection closed.")
44
45
if __name__ == "__main__":
46
    asyncio.run(main())

1
import wave
2
import asyncio
3
from groq import Groq
4
from smallestai.waves import WavesClient, TextToAudioStream
5
6
# Initialize Groq (LLM) and Smallest (TTS) instances
7
llm = Groq(api_key="GROQ_API_KEY")
8
tts = WavesClient(api_key="SMALLEST_API_KEY")
9
10
# Async function to stream text generation from LLM
11
async def generate_text(prompt):
12
    completion = llm.chat.completions.create(
13
        messages=[{"role": "user", "content": prompt}],
14
        model="llama3-8b-8192",
15
        stream=True,
16
    )
17
18
    # Yield text as it is generated
19
    for chunk in completion:
20
        text = chunk.choices[0].delta.content
21
        if text:
22
            yield text
23
24
# Async function to save generated audio as a WAV file
25
async def save_audio_to_wav(file_path, processor, llm_output):
26
    with wave.open(file_path, "wb") as wav_file:
27
        wav_file.setnchannels(1)       # Mono audio
28
        wav_file.setsampwidth(2)       # 16-bit samples
29
        wav_file.setframerate(24000)   # 24 kHz sample rate
30
        
31
        # Process audio chunks and write them to the WAV file
32
        async for audio_chunk in processor.process(llm_output):
33
            wav_file.writeframes(audio_chunk)
34
35
# Main asynchronous function to run the process
36
async def main():
37
    # Initialize the TTS processor
38
    processor = TextToAudioStream(tts_instance=tts)
39
    
40
    # Generate text asynchronously
41
    llm_output = generate_text("Explain text to speech like I am five in 5 sentences.")
42
    
43
    # Save the generated speech to a WAV file
44
    await save_audio_to_wav("llm_to_speech.wav", processor, llm_output)
45
46
if __name__ == "__main__":
47
    asyncio.run(main())