Custom Voice Creator ๐๏ธ
Blend 2โ5 base Kokoro voices with adjustable weights to create unique new timbres.
Preview instantly, fine-tune the blend, then download the .bin file
for use with the Kokoro TTS engine. Everything runs in your browser.
Load Model
Download Kokoro-82M (~305MB) once. Cached in browser.
Pick & Blend
Select 2-5 base voices, adjust weight sliders to taste.
Preview
Type test text and hear the blended voice instantly.
Download
Save your blend as a .bin file for use anywhere.
How voice blending works
Each Kokoro voice is stored as a .bin file containing a Float32Array
of style embedding vectors (256 elements per token position). Blending computes a
weighted average: for each position i in the embedding array,
blend[i] = ฮฃ(wโฑผ ร voiceโฑผ[i]) / ฮฃ(wโฑผ).
The result is a new .bin file that works immediately with the standard Kokoro-82M ONNX model โ no retraining, no fine-tuning. The blend captures characteristics from all source voices proportional to their weights.
Language handling: The dominant base voice (highest weight) determines the language for phonemization. English uses kokoro-js's built-in phonemizer; non-English voices phonemize via the OfflineTTS API. Audio synthesis always runs locally.