Advertisement
Adsterra privacyVoice Packs 📦
A starter set of 13 curated blend recipes from the lab’s 55 generated combinations — ASMR whispers, audiobook narrators, anime characters, professional anchors, and more. Open any pack in the designer, tweak it on the map, and make it yours.
🇯🇵 Jp Cute Anime
same-languageJapanese
Nezumi 40% + Gongitsune 30% + Tebukuro 30%
Fixed sample transcript
今朝はコーヒーをいれる前に窓を開けました。通りはまだ静かで、木の下を自転車がゆっくり通っていきます。今日やることを三つだけ書き出してから、まずは朝ごはんをゆっくり食べることにしました。急がない時間があるだけで、いつもの朝が少しやわらかく感じられます。
🇬🇧 Uk Elegance
same-languageBritish English
Emma 60% + Fable 40%
Fixed sample transcript
I put the kettle on before opening my laptop this morning. While the tea was brewing, I stood by the window and watched the clouds move over the rooftops. It was a gentle way to begin a day that looked busy on paper.
🇺🇸 Warm Flame
same-languageAmerican English
Heart 60% + Bella 40%
Fixed sample transcript
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.
🇨🇳 Zh Deep Male
same-languageMandarin Chinese
Yunyang 50% + Yunjian 30% + Yunxia 20%
Fixed sample transcript
今天早上，我在煮咖啡前先打开了窗。街上还很安静，一辆送货的自行车慢慢经过树下。我只写下三件今天要做的小事，然后决定先好好吃早餐。原来不用急着开始，也能让平常的早晨变得轻松一些。
🇨🇳 Zh Professional M
same-languageMandarin Chinese
Yunjian 45% + Yunxi 35% + Yunyang 20%
Fixed sample transcript
今天早上，我在煮咖啡前先打开了窗。街上还很安静，一辆送货的自行车慢慢经过树下。我只写下三件今天要做的小事，然后决定先好好吃早餐。原来不用急着开始，也能让平常的早晨变得轻松一些。
🇨🇳 Zh Sweet Girl
same-languageMandarin Chinese
Xiaoyi 45% + Xiaobei 35% + Xiaoxiao 20%
Fixed sample transcript
今天早上，我在煮咖啡前先打开了窗。街上还很安静，一辆送货的自行车慢慢经过树下。我只写下三件今天要做的小事，然后决定先好好吃早餐。原来不用急着开始，也能让平常的早晨变得轻松一些。
🇨🇳 Zh Warm Lady
same-languageMandarin Chinese
Xiaoxiao 50% + Xiaoni 30% + Xiaoyi 20%
Fixed sample transcript
今天早上，我在煮咖啡前先打开了窗。街上还很安静，一辆送货的自行车慢慢经过树下。我只写下三件今天要做的小事，然后决定先好好吃早餐。原来不用急着开始，也能让平常的早晨变得轻松一些。
🇺🇸 Audiobook
same-familyAmerican English
Heart 40% + Michael 30% + Emma 30%
Fixed sample transcript
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.
🇺🇸 Asmr Whisper
experimentalAmerican English
River 40% + Sarah 35% + Gongitsune 25%
Fixed sample transcript
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.
🇺🇸 Eastwest F
experimentalAmerican English
Heart 50% + Xiaoxiao 30% + Alpha 20%
Fixed sample transcript
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.
🇫🇷 Euro Delight
experimentalFrench
Siwis 35% + Sara 35% + Dora 30%
Fixed sample transcript
Ce matin, j’ai ouvert la fenêtre avant de faire du café. La rue était encore calme et un vélo de livraison est passé doucement sous les arbres. J’ai noté trois choses à faire aujourd’hui, puis j’ai décidé que la première pouvait attendre après le petit déjeuner.
🇯🇵 Sakura Dream
experimentalJapanese
Alpha 40% + Heart 40% + Gongitsune 20%
Fixed sample transcript
今朝はコーヒーをいれる前に窓を開けました。通りはまだ静かで、木の下を自転車がゆっくり通っていきます。今日やることを三つだけ書き出してから、まずは朝ごはんをゆっくり食べることにしました。急がない時間があるだけで、いつもの朝が少しやわらかく感じられます。
Why only blends?
Packs reproduce exactly through the designer’s weighted-average synthesis — every pack is a convex combination of real base voices, so what you hear matches the recipe. Vector-math, extrapolation, recombine, and PCA-sampled recipes are less predictable; they stay in the experiment lab with their full recipe metadata.
Frequently asked questions
What are voice packs?
Voice packs are curated blend recipes: weighted combinations of real Kokoro voice embeddings, generated offline from the lab’s 55 experimental recipes. Only convex blends are promoted here because they reproduce exactly in the designer.
How do I use a pack?
Click “Open in Designer” and the pack loads into the Voice Maker studio. Press Preview (the model downloads once, ~305MB) to hear it, tweak it on the map, save your version, or download the .bin style file.
Why are some packs labeled experimental?
Packs that mix distinct language families (e.g. English + Japanese + Mandarin) are labeled experimental: they can sound less natural. Packs blending voices from one language or language family are labeled same-language or same-family.
Are packs free and do they require an account?
Everything is free with no signup or API key. Recipes are just numbers; the designer rebuilds each pack from the real base-voice style files in your browser.
Can I modify a pack?
Yes — after loading a pack you can keep dragging the map or adjusting traits, then save your version to My Voices or share it as a link.