Or jump from this list on a smaller screen.

This is a page from the Audivra documentation. Developer exportsindex: http://127.0.0.1:3000/docs/llms.txt, full corpus: http://127.0.0.1:3000/docs/llms-full.txt, OpenAPI: http://127.0.0.1:3000/docs/openapi.json, Postman: http://127.0.0.1:3000/docs/postman.json. Press ⌘K to search docs.

Voice library

Five voice types — presets, clones, remixes, prompt-based design, and community listings. Browse presets, then unlock custom voices on paid plans. Each type returns a voice_id for TTS and generate.

Preset voices

Ship with Audivra — regional Swahili, Hausa, Yoruba, Hindi, and more.

Play a sample, copy voice_id, and use immediately in TTS or generate — no training required.

Browse preset library ↓

Cloned voices

Upload 5–10s audio samples to clone any speaker.

F5-TTS or XTTS v2 training on GPU. Instant cloning uses short samples; professional cloning (Creator+) trains on 2–30 minutes of speech.

Cloned voices guide →

Voice design

Describe a voice in text — gender, age, accent, tone.

Generate a speaker reference from a prompt. Preview before saving. Shares custom voice slots with cloning.

Voice design guide →

Voice remix

Describe a change to a clone you own — tone, pacing, accent.

Creates a new voice_id without replacing the parent. Uses one custom voice slot.

Voice remix guide →

Community marketplace

Publish a ready clone or license someone else's listing as voice_id.

Consent required to publish. Optional per-use credit fee. Listings do not consume extra slots.

Marketplace guide →

Preset voice library

16 preset voices ship with Audivra — play a sample, copy voice_id, and paste into POST /api/v1/tts or POST /api/v1/generate. Custom voices (clone or design) share plan slots — see Credits.

Popular regional picks

African regional
sw-KE

Zuri

Swahili — WAXAL / OpenBibleTTS

zuri-sw

Engine: kokoro-82m · Female

African regional
ha-NG

Umar

Hausa regional voice

umar-ha

Engine: kokoro-82m · Male

African regional
yo-NG

Ezinne

Yoruba regional voice

ezinne-yo

Engine: kokoro-82m · Female

South Asian
hi-IN

Swara

Hindi — low VRAM Kokoro-82M

swara-hi

Engine: kokoro-82m · Female

African regional

African regional
sw-KE

Zuri

Swahili — WAXAL / OpenBibleTTS

zuri-sw

Engine: kokoro-82m · Female

African regional
ha-NG

Umar

Hausa regional voice

umar-ha

Engine: kokoro-82m · Male

African regional
yo-NG

Ezinne

Yoruba regional voice

ezinne-yo

Engine: kokoro-82m · Female

African regional
am-ET

Mekdes

Amharic regional voice

mekdes-am

Engine: kokoro-82m · Female

African regional
zu-ZA

Thando

Zulu regional voice

thando-zu

Engine: kokoro-82m · Male

South Asian

South Asian
hi-IN

Swara

Hindi — low VRAM Kokoro-82M

swara-hi

Engine: kokoro-82m · Female

South Asian
bn-IN

Tanishaa

Bengali regional voice

tanishaa-bn

Engine: kokoro-82m · Female

English

English
en-US

Aurora

Warm studio narrator

aurora

Engine: kokoro · Female

English
en-GB

Holloway

Broadcast baritone

holloway

Engine: kokoro · Male

English
en-US

Mira

Conversational, bright

mira

Engine: f5-tts · Female

English
en-US

Nile

Low-latency API default

nile

Engine: kokoro-82m · Neutral

European

European
fr-FR

Solenne

Expressive, streaming

solenne

Engine: cosyvoice-2 · Female

European
de-DE

Klara

German studio narrator

klara-de

Engine: kokoro-82m · Female

European
it-IT

Marco

Italian conversational voice

marco-it

Engine: kokoro-82m · Male

European
nl-NL

Lotte

Dutch clear narrator

lotte-nl

Engine: kokoro-82m · Female

East Asian

East Asian
ja-JP

Kenji

Multilingual clone-ready

kenji

Engine: xtts-v2 · Male

Use a copied voice_id in POST /api/v1/tts or the docs TTS playground, generate playground. List programmatically: GET /api/v1/voices