Write a script to get jwt token for a room, and th...
# ask-aii
icy-country-64454
05/12/2025, 12:49 PMWrite a script to get jwt token for a room, and then connect to the room to publish audio track via rtc using livekit v1.0
t
tall-airline-16756
05/12/2025, 12:49 PMThanks for reaching out, Raghav. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
tall-airline-16756
05/12/2025, 12:49 PMI couldn't locate a complete script for generating a JWT token and connecting to a room to publish an audio track using LiveKit v1.0. However, I found a partial code snippet for token generation. If you'd like, I can escalate this to a human specialist for further assistance or provide additional guidance on specific parts of the implementation. Sources: Tree View: | dse-workbench | React Native quickstart | LiveKit Docs
i
icy-country-64454
05/12/2025, 12:51 PMCode snippet to publish audio track via rtc
t
tall-airline-16756
05/12/2025, 12:52 PMHere is a code snippet for publishing an audio track via RTC using LiveKit:
Copy code
import numpy as np
from livekit import agents, rtc
SAMPLE_RATE = 48000
NUM_CHANNELS = 1 # mono audio
AMPLITUDE = 2 ** 8 - 1
SAMPLES_PER_CHANNEL = 480 # 10 ms at 48kHz
async def entrypoint(ctx: agents.JobContext):
await ctx.connect()
# Create audio source and track
source = rtc.AudioSource(SAMPLE_RATE, NUM_CHANNELS)
track = rtc.LocalAudioTrack.create_audio_track("example-track", source)
# Set options for publishing
options = rtc.TrackPublishOptions(source=rtc.TrackSource.SOURCE_MICROPHONE)
# Publish the track
publication = await ctx.agent.publish_track(track, options)
# Example of sending audio frames (sine wave)
frequency = 440
async def _sinewave():
audio_frame = rtc.AudioFrame.create(SAMPLE_RATE, NUM_CHANNELS, SAMPLES_PER_CHANNEL)
audio_data = np.frombuffer(audio_frame.data, dtype=np.int16)
total_samples = 0
while True:
time = (total_samples + np.arange(SAMPLES_PER_CHANNEL)) / SAMPLE_RATE
sinewave = (AMPLITUDE * np.sin(2 * np.pi * frequency * time)).astype(np.int16)
np.copyto(audio_data, sinewave)
# Send this frame to the track
await source.capture_frame(audio_frame)
total_samples += SAMPLES_PER_CHANNEL
await _sinewave()