Multi-Speaker Kokoro Podcast Timeline
Assign different Kokoro voices and speeds per speaker, then render the full conversation at once.
Interactive Karaoke Stage (Click any word to seek)
Batch 0 / 0
Click Generate & Play Full Text to synthesize and track words in real time.
Packed Neural Batches (Smart Context Packing — Click to Jump)
0 Batches
Characters
0
Words
0
Neural Batches
0
Track Length
00:00
Track Status
Not Rendered
Synthesizing full text in background Web Workers...
0%
VISEME: IDLE
0% OPEN
Ready to render
Live FFT Acoustic Analyzer
24kHz PCM
00:00.0
Current Status: Initializing Kokoro-82M...
00:00.0
FULL-TRACK TIMELINE (CLICK OR DRAG TO SEEK)
Generate full text to inspect waveform