Many voices
26 curated Chinese & English male/female voices, including Northeastern/Shaanxi accents and American/British English — switch with a tap.
Turn text into natural speech — Chinese and English, 26 voices to pick from, free preview and WAV download.
Privacy-sensitive steps are processed in your browser, and data is destroyed when you close the page.
No 20- or 30-minute ceilings — clean, complete exports with no watermark or audio bumpers added.
Runs right in your desktop or mobile browser — no download needed.
Sign in with your WUJIEE account to use it for free, watermark-free.
Privacy-sensitive steps run in your browser, and data is destroyed when you close the page. Work on meeting recordings, interviews and personal voice notes with confidence.
26 curated Chinese & English male/female voices, including Northeastern/Shaanxi accents and American/British English — switch with a tap.
Preview the result online or download it as a 24kHz WAV file, with 0.5–2× adjustable speed.
Privacy-sensitive steps are processed on-device and data is destroyed on page close; we never store your text.
Sign in, enter text and pick a voice
Click Synthesize (first use loads ~120MB of resources)
Preview and download the WAV
26 curated male and female voices — Chinese with Northeastern and Shaanxi accents, and English in both American (af/am) and British (bf/bm) accents. Tap a voice card to switch and preview; export WAV like every other voice.
Paste the text, pick a voice and speed (0.5–2×), synthesize and preview, then download the 24kHz WAV for offline listening or narration.
It's free after sign-in, with watermark-free exports; long articles can be synthesized in sections — no forced membership or per-character paywall.
Yes. Several English voices are built in (American and British, male and female) for English narration and read-aloud; Chinese numbers and dates are read out in Chinese automatically.
Yes. Privacy-sensitive synthesis is processed on-device, and your data is destroyed when you close the page; we never store your text. The first synthesis loads ~120MB, cached by the browser afterwards.
13 online audio tools: convert, trim, denoise, separate vocals, transcribe speech and more — all in one place.
Browse all tools