Skip to content
Generated illustration for Heart, a American English female Kokoro voice

Heart

Grade A Kokoro

🇺🇸 American English · ♀ Female Voice

warm natural
Listen to natural sample audio
Use Heart Voice in TTS →

About the Heart Voice

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

Voice character: Warm, Natural

Best for: Storytelling & narration

How to use the Heart voice:

  • Open the TTS tool
  • "Heart" will be automatically selected in the voice picker
  • Type or paste your text (up to 50,000 characters per batch)
  • Click generate — speech is created locally on your device
  • Download as uncompressed WAV or compact MP3

Quality rating explained: A 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 Heart 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: “This morning I opened the window before making coffee. The street was still quiet, and a delivery bike passed slowly beneath the trees. I made a small list for the day, then decided the first item could wait until after breakfast.” 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: An A grade marks the strongest assets in this catalog. It still describes general listening impressions across a fixed set of prompts, not a measurement on your script.

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 0ab5709b, 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: Bella (female, grade A-), Nicole (female, grade B-), Alloy (female, grade C). 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.

Best For: Storytelling & narration

Heart's warm, natural tone makes it ideal for storytelling, audiobooks, educational content, and any project that needs a friendly, engaging voice.

Generate speech with Heart now →

Heart Voice — Frequently Asked Questions

Is the Heart voice free to use?

Yes. The Heart voice is completely free. It runs in your browser with no API key, no signup, and no subscription limits. OfflineTTS has no per-character charge. Device resources, model downloads, and review time remain constraints.

Does the Heart voice work offline?

Yes. After the initial model download is cached in your browser, the Heart voice can generate speech completely offline without internet connectivity.

What quality rating does the Heart voice have?

The catalog label A is an editorial discovery aid, not a standardized listening benchmark. Review your actual output for pronunciation, artifacts, pacing, and suitability.

Can I export WAV and MP3 with Heart?

Yes. After generating speech with Heart, you can download uncompressed 24kHz WAV files for studio editing or compressed MP3 files for sharing and publishing.

Can I use the Heart voice for commercial projects?

Review the selected model and voice asset license, source-text rights, and any reference recording permissions before commercial use. Software licenses do not grant every speaker or copyright permission. See our Transparency page and Terms.

Ready to use Heart?

Experience natural American English speech synthesis in your browser with zero setup or character fees.

Open Heart Voice in TTS Studio →