Labs · Voice gallery
96 voices,
one sentence.
Every provider demos its voices on a different marketing line, which makes comparing them guesswork. Here all 96 voices read the same sentence — filter by provider, gender, language or style, tap through, and pick the narrator for your next audiobook.
96 voices · 96 samples · generated 2026-07-24 · 17–31KB each, loaded on tap
Every voice reads the same sentence, so you compare voices — not scripts:
Chinese voices read: “晚风翻动书页，灯下的故事才刚刚开始。”
English voices read: “The wind turns a page, and under the lamp the story is just beginning.”
Alibaba DashScope Qwen-TTSqwen3-tts-flash · 49 voices
- CherryFemaleChinese
Sunny, friendly young woman
- SerenaFemaleChinese
Gentle young woman
- EthanMaleChinese
Warm, energetic young man
- ChelsieFemaleChinese
Anime-style virtual girlfriend
- MomoFemaleChinese
Playful and cute
- VivianFemaleChinese
Sassy and adorable
- MoonMaleChinese
Carefree and dashing
- MaiaFemaleChinese
Wisdom meets warmth
- KaiMaleChinese
A spa for your ears
- AndreMaleChinese
Magnetic, steady male voice
- NofishMaleChinese
Designer who can't roll his R's
- BellaFemaleChineseCharacter
Spirited little girl
- BunnyFemaleChineseCharacter
Overflowing cuteness
- MiaFemaleChineseCharacter
Docile and sweet
- NiniFemaleChineseCharacter
Soft, sticky-sweet voice
- StellaFemaleChineseCharacter
Ditzy magical girl
- MochiMaleChineseCharacter
Clever precocious kid
- PipMaleChineseCharacter
Mischievous kid full of wonder
- RyanMaleChineseCharacter
Rhythmic, dramatic delivery
- KaterinaFemaleChineseCharacter
Mature, memorable cadence
- BellonaFemaleChineseCharacter
Powerful storytelling voice
- VincentMaleChineseCharacter
Raspy, weathered narrator
- ArthurMaleChineseCharacter
Rustic voice steeped in years
- NeilMaleChineseCharacter
Professional news anchor
- EliasFemaleChineseCharacter
Rigorous yet narrative lecturer
- SerenFemaleChineseCharacter
Soothing sleep companion
- EbonaFemaleChineseCharacter
Whisper from the darkest corner
- Eldric SageMaleChineseCharacter
Calm and wise elder
- Ono AnnaFemaleChineseCharacter
Clever, spirited childhood friend
- Radio GolMaleChineseCharacter
Football poet commentator
- JenniferFemaleEnglishCharacter
Cinematic American English
- AidenMaleEnglishCharacter
American boy who loves cooking
- SoheeFemaleKoreanCharacter
Warm, expressive Korean unnie
- BodegaMaleSpanishCharacter
Passionate Spanish uncle
- SonrisaFemaleSpanishCharacter
Cheerful Latina
- AlekMaleRussianCharacter
Cold outside, warm inside
- DolceMaleItalianCharacter
Laid-back Italian uncle
- LennMaleGermanCharacter
Rational with hidden rebellion
- EmilienMaleFrenchCharacter
Romantic French gentleman
- DylanMaleChineseDialect
Beijing hutong youth
- JadaFemaleChineseDialect
Fast-paced Shanghai auntie
- SunnyFemaleChineseDialect
Sweet Sichuan girl
- EricMaleChineseDialect
Chengdu street vibe
- RockyMaleCantoneseDialect
Humorous Cantonese chat
- KikiFemaleCantoneseDialect
Sweet Hong Kong bestie
- LiMaleChineseDialect
Patient yoga teacher
- MarcusMaleChineseDialect
Authentic Shaanxi flavor
- RoyMaleChineseDialect
Lively Taiwanese lad
- PeterMaleChineseDialect
Tianjin crosstalk sidekick
xAI Grok Voicegrok-voice-latest · 26 voices
- AraFemaleMultilingual
Upbeat and expressive
- EveFemaleMultilingual
Warm and friendly (default)
- LeoMaleMultilingual
Confident and steady
- RexMaleMultilingual
Calm and grounded
- SalNeutralMultilingual
Smooth and neutral
- LumenMultilingual
- CastorMultilingual
- NakshMultilingual
- AtlasMultilingual
- CarinaMultilingual
Support: patient and clear
- ZaganMultilingual
- HelixMultilingual
- OrionMultilingual
- LunaMultilingual
Wellness: soft and soothing
- IrisMultilingual
- AltairMultilingual
- ZenithMultilingual
- PerseusMultilingual
- HeliosMultilingual
- LuxMultilingual
- KeplerMultilingual
- RigelMultilingual
- CosmoMultilingual
- CelesteMultilingual
- UrsaMultilingual
- SiriusMultilingual
OpenAIgpt-4o-mini-tts · 13 voices
- AlloyNeutralMultilingual
Balanced and neutral
- AshMaleMultilingual
Steady and composed
- BalladMaleMultilingual
Lyrical storytelling
- CoralFemaleMultilingual
Bright and upbeat
- EchoMaleMultilingual
Even and clear
- FableNeutralMultilingual
British narrative flair
- NovaFemaleMultilingual
Energetic and friendly
- OnyxMaleMultilingual
Deep and resonant
- SageFemaleMultilingual
Gentle and mellow
- ShimmerFemaleMultilingual
Light and crisp
- VerseMaleMultilingual
Expressive and agile
- MarinFemaleMultilingual
Confident and warm
- CedarMaleMultilingual
Natural conversational
SiliconFlow CosyVoice2FunAudioLLM/CosyVoice2-0.5B · 8 voices
- AlexMaleChinese
Steady male voice
- BenjaminMaleChinese
Low, mellow male voice
- CharlesMaleChinese
Magnetic male voice
- DavidMaleChinese
Cheerful male voice
- AnnaFemaleChinese
Steady female voice
- BellaFemaleChinese
Passionate female voice
- ClaireFemaleChinese
Gentle female voice
- DianaFemaleChinese
Cheerful female voice
The sample is the trailer: in the app, this voice reads your whole book, chapter after chapter.
Listen to your own book with this voiceWhere the catalog and samples come from
The voice list is the app's built-in catalog, checked against each provider's official docs in July 2026: 49 DashScope Qwen-TTS voices (including the dialect and character sets), 26 xAI Grok voices, 13 OpenAI voices, 8 SiliconFlow CosyVoice2 presets. Names, gender labels and dialect/character groupings follow the official product pages; where a provider doesn't publish gender, the tag says so instead of guessing.
Samples were batch-synthesized once on 2026-07-24 through each provider's own API, then normalized: mono MP3, matched loudness across providers, 17–31KB per file. Same-sentence design is the point of the page — one Chinese sentence for Chinese-locale voices, one English sentence for the rest — so what varies between two rows is the voice, never the script. The OpenAI batch was synthesized through an aggregator gateway carrying the same official voice models, noted here for the record.
What a 5-second sample can't tell you
These are one-off snapshots, not live synthesis — providers update their voice models, so today's sample and tomorrow's in-app rendering can drift apart in pacing or emotional delivery. A short sentence shows a voice's basic color, but long-form narration (sentence breaks, chapter pauses, stamina over an hour) only proves itself on a real book in the app. And gender tags for OpenAI and the newer xAI voices are community consensus or left unlabeled, because the vendors don't publish them.
FAQ
How were these samples generated?
One-off batch on 2026-07-24: each of the 96 voices synthesized one short sentence through its provider's own TTS API — Alibaba DashScope qwen3-tts-flash, xAI grok-voice-latest, OpenAI gpt-4o-mini-tts, SiliconFlow CosyVoice2. Everything was then converted to mono MP3 at matched loudness, 17–31KB per file. Chinese-locale voices read one Chinese sentence, everything else reads one English sentence — so the differences you hear come from the voices, not the script.
Why might a voice have no sample?
The catalog mirrors the app's built-in 96-voice list. If a provider call fails or a channel is unavailable when samples are regenerated, that voice is honestly marked "no sample yet · available in app" instead of being faked with a different recording. This batch came back 96 for 96; future catalog updates follow the same rule.
Is listening here paid? How does pricing work in the app?
This page serves static files — tap as much as you like, nothing is billed and nothing is synthesized live. In the app, audiobook listening is real synthesis billed by volume: the official channel charges list price plus a 50% service fee per character against your credits (the 5,000-credit signup grant covers a few chapters of listening), or you can bring your own provider key and pay your own bill directly.