Jetson Audio Service

X-API-Key:

Speech-to-Text (Whisper)

Upload Audio File: Whisper Model Size:

Select model size based on accuracy vs speed tradeoff.

Enable Smart Split (Better for long files/podcasts)

Splits audio on silence for better transcription of long recordings.

Transcription:

Text-to-Speech (Qwen3 Cloning)

TTS Model:

Input Text (Auto-detects CN/EN): Speaker Reference (Optional):

Select a speaker voice reference. Auto-detects Chinese vs English if not specified.

Speed:

Speech speed multiplier (0.5 = slow, 2.0 = fast).

Generated Audio:

Download .wav