WhisperWeb TTS
engine…
device ·
cache ·
model none
Text to speak 0 chars
Tip: Ctrl+Enter generate
Ready: pick a model on the right.
Audio ·
No audio yet. Generate from text above. Streaming shows chunks live.
model ·
voice ·
time ·
speed ·
1 · TTS Model: superfast
TinyTTS 3.4MB 1.6M 53× Kokoro · Kokoro 82M 70-93MB q4/q8 small · MMS 38MB English+Hindi only (French/Spanish/etc removed). All cache offline.
Models fetch once from Hugging Face CDN, then cached: offline forever.
2 · Voice & Options
Kokoro has 11+ voices: Heart is best all-rounder. MMS/Speecht5 use default voice.
1.00×
Streaming uses
TextSplitterStream for long text: chunks play as they generate.History local only
TTS audio saves here (IndexedDB, never leaves device). Click to replay.