Voices & languages

List the catalog

GET https://api.satryx.ai/voice/voices returns every available voice — the VocaBusta African-language voices, plus any voices you've cloned. This endpoint is ungated, so you can browse before subscribing.

curl https://api.satryx.ai/voice/voices \
  -H "Authorization: Bearer $SATRYX_API_KEY"

Each voice looks like:

{
  "id": "vocabusta_yo_female",
  "name": "Adunni",
  "description": "Yoruba female voice from the VocaBusta model.",
  "accent": "Yoruba",
  "gender": "female",
  "category": "vocabusta",
  "language": "yo",
  "language_name": "Yoruba",
  "tags": ["vocabusta", "yo", "female"],
  "preview_url": "https://…/previews/vocabusta_yo_female.wav",
  "engine": "vocabusta"
}

• category is vocabusta (catalog), cloned (your clones) or premade (shared fallback voices).
• preview_url is a short, browser-playable sample (may be null).

Voice IDs

The named primary voice for each language follows the pattern vocabusta_<language>_<gender> — e.g. vocabusta_pcm_female, vocabusta_ha_male. The catalog also exposes additional per-speaker variants for some languages.

Language	Code	Female	Male
Nigerian Pidgin	pcm	Blessing	Sunday
Yoruba	yo	Adunni	Tunde
Igbo	ig	Adaeze	Emeka
Hausa	ha	Zainab	Sani
Nigerian English	en_ng	Tiwa	Obinna
Ghanaian English	en_gh	Ama	Kwame
Kenyan English	en_ke	Wanjiru	Otieno
Twi / Akan	tw	Akosua	Kofi
Dagbani	dag	Lamisi	Mahama
Ewe	ee	Esinam	Senyo
Swahili	sw	Imani	Juma
Zulu	zu	Thandeka	Sipho

Example IDs: vocabusta_pcm_female (Blessing), vocabusta_sw_male (Juma).

The pod's live registry is the source of truth; always pull GET /voice/voices at runtime rather than hard-coding the full roster. The table above is the guaranteed named pair per language.

Language support by feature

Not every language is available for every operation yet.

Code	Text to speech	Transcription (STT)	Dubbing target
pcm (Nigerian Pidgin)	✅	✅	—
yo (Yoruba)	✅	✅	✅
ig (Igbo)	✅	beta	✅
ha (Hausa)	✅	✅	✅
en_ng (Nigerian English)	✅	✅	✅ (en)
en_gh (Ghanaian English)	✅	✅	✅ (en)
en_ke (Kenyan English)	✅	✅	✅ (en)
sw (Swahili)	✅	✅	✅
zu (Zulu)	✅	—	✅
tw (Twi)	✅	—	—
dag (Dagbani)	✅	—	—
ee (Ewe)	✅	—	—

• STT routes African languages to the Vocabanga ASR model and falls back to Whisper for the rest. See Speech to text.
• Dubbing targets are languages we can both translate into and synthesize. See Dubbing.