GluePuddingTool

AI Voice Sample Recorder

Record or upload a Chinese reading sample, automatically validate MP3/M4A/WAV format, 10 seconds–5 minutes duration and 20MB size, and export a WAV file.

FreeOnline Tool
Loading…

Support this site

Always free. Tipping is entirely optional.

Customer Service

Click to view QQ number
877716587

How to Use

Choose a classic Chinese reading passage, click “Start Recording”, allow microphone access in the browser prompt, and begin reading after the 3-second countdown. The timer, waveform and input level update live. The stop button becomes available after 10 seconds, and recording stops automatically at 5 minutes.

The tool then creates a 32kHz, 16-bit, mono WAV file that you can preview and download. Recording and encoding happen entirely in your browser; audio is never uploaded to a server and is cleared when you refresh the page.

If you already have a recording, switch to “Upload Audio”. MP3, M4A and WAV are supported. The tool reads the file metadata and validates format, size (max 20MB) and duration (10 seconds–5 minutes). Valid files can be previewed or downloaded; invalid files show each failed requirement.

The reading library includes excerpts from Zhu Ziqing’s “Spring”, Xu Zhimo’s “Farewell to Cambridge” and Li Bai’s “Invitation to Wine”, with tone and emotion labels plus a Mandarin four-tone warm-up. Use a quiet room, a stable microphone distance and a natural speaking pace. Only record your own voice or a voice you have explicit permission to clone.

Features

  • Local PCM recording in the browser; audio never leaves your device
  • Three famous Chinese reading passages with tone and emotion labels
  • Mandarin four-tone warm-up to help you get ready
  • Record 10 seconds–5 minutes, with automatic stop at 5 minutes
  • Live timer, waveform and input level meter
  • Export 32kHz / 16-bit / mono WAV, under 20MB even at 5 minutes
  • Upload MP3, M4A or WAV with automatic format, size and duration checks
  • Preview and download both recorded and uploaded files

Use Cases

AI voice cloning
Record 1–3 minutes of natural, expressive Chinese speech as a voice cloning or training sample.
Dubbing and virtual hosts
Capture different emotional tones to make synthesized speech more expressive and recognizable.
Upload compliance checks
Upload an existing file to quickly verify whether its format, size and duration meet AI platform requirements.

FAQ

Why does the recorder export WAV?
WAV is an uncompressed, high-quality format accepted by common AI voice platforms. This tool exports 32kHz, 16-bit, mono WAV, keeping speech clear while staying under 20MB for a 5-minute file. Existing uploads may be MP3 or M4A.
How long should the sample be?
At least 10 seconds; 1–3 minutes is recommended. Include varied intonation, natural pauses and emotional shifts. The maximum is 5 minutes, after which recording stops automatically.
Is my audio uploaded to a server?
No. Microphone capture, WAV encoding, validation and playback all happen locally in your browser. Audio is not sent to a server and is cleared when you refresh the page.
Why can’t the uploader read my file duration?
The file may be damaged, the extension may not match the actual codec, or your browser may not support the encoding. Confirm it plays in a media player, then convert it to standard MP3 or WAV and try again.
Why is the stop button disabled for the first 10 seconds?
AI voice samples usually require at least 10 seconds. The tool enforces this to prevent unusable short clips. Recording 1–3 minutes generally produces a better training sample.
Can I record someone else’s voice?
Only if you own the voice or have explicit permission from its owner. Cloning another person’s voice without consent may be illegal and violates AI platform rules.