Habibi-TTS Inference Endpoint Handler

Custom inference endpoint handler for Habibi-TTS โ€” a zero-shot Arabic TTS model supporting 12 dialects.

Usage

Deploy this repo as a Hugging Face Inference Endpoint (Dedicated) with a GPU instance (T4 or better).

Request Format

{
  "ref_audio_url": "https://example.com/reference.wav",
  "ref_text": "Transcription of the reference audio",
  "gen_text": "ุงู„ู†ุต ุงู„ุนุฑุจูŠ ุงู„ู…ุฑุงุฏ ุชุญูˆูŠู„ู‡ ุฅู„ู‰ ูƒู„ุงู…",
  "dialect": "SAU",
  "speed": 1.0,
  "nfe_step": 32,
  "cross_fade_duration": 0.15,
  "seed": -1,
  "remove_silence": false
}

Supported Dialects

Code Dialect
SAU Saudi Arabic (Najdi)
GLF Gulf Arabic
EGY Egyptian Arabic
IRQ Iraqi Arabic
UAE Emirati Arabic
ALG Algerian Arabic
MAR Moroccan Arabic
MSA Modern Standard Arabic
LBN Lebanese Arabic
SYR Syrian Arabic
JOR Jordanian Arabic
TUN Tunisian Arabic

Response

Returns raw WAV audio bytes (audio/wav).

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support