Jessica

Jessica is a female American English AI voice rated D on the OfflineTTS quality scale. Speech synthesis runs in your browser with no signup or per-character fees.

Best for: General voice-over

Quality rating explained: D is a catalog discovery label, not a measured MOS score, a public leaderboard position, or a guarantee for your script. Audition names, numbers, pacing, and chunk joins before publishing.

The Jessica voice uses Kokoro's browser phonemizer and local WebGPU or WebAssembly synthesis. After the initial model download, English generation works completely offline.

Preview transcript: the sample player above reads: “A friend sent a message asking if I wanted to walk by the river after work. We did not have a big plan, just comfortable shoes and enough time to watch the light change on the water. Sometimes that is exactly what a day needs.” Listen to that clip before generating your own text; it is the shortest way to judge pronunciation, pace, and whether the American English phonemization path fits your script.

Reviewing American English text with this preset: American English is stress-timed, so an unnatural emphasis can make an otherwise clean render sound wrong. Check contractions, acronyms (spoken as letters or as a word), dates, and dollar amounts, and keep one sentence per line when a long script starts to drift.

Grade context: A D grade marks a visibly weaker asset. Use it knowingly, in short takes, and only when its specific texture is the point.

What the browser downloads: English Kokoro ships two model files here: a 305 MB 4-bit build and a 326 MB full-precision build. The browser downloads one of them on first use and keeps it in cache; the phonemizer for English also runs locally.

Asset identity: this preset maps to the cached asset fingerprint cdfdccb8, so it can be told apart from a same-named voice on another engine even when the label in the picker looks identical.

Other American English voices: Heart (female, grade A), Bella (female, grade A-), Nicole (female, grade B-). Switching between them on the same sentence is the fastest way to hear whether one suits the script better.

Explore other American English voices or browse the complete voice library for your project.