Indic Parler TTS TTS
High-quality speech for 11 Indian languages with natural-language voice control and no preset voices.
Kpọchie ngwe gị n'ime SSML táàbụ̀ maka nlekọta ziri ezi:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Táàbụ̀ nke móòdù ahụ a họọrọ na-aghọta - pịa ka ịkpụga otu n'ime ngwe gị ebe ọ na-eme:
Móòdù a na-agụ ngwe nkịtị, yabụ na a na-ewepụta inline táàbụ̀. Maka táàbụ̀-n'okpuru n'émóòdù, gbanwee ka móòdù na-egosi ihe dịka Orpheus mọọbụ Bark.
Ndesịta okwu emeredịkachọrọ:
_N'ihe banyere Indic Parler TTS
Indic Parler TTS by AI4Bharat extends the Parler architecture to the Indian subcontinent, generating natural speech across Tamil, Bengali, Marathi, Gujarati, Kannada, Punjabi, Odia, Assamese, Hindi, Telugu, Malayalam, and English. Like Parler, it has no preset voice list — instead you describe the voice you want in plain language and the model produces speech matching that description. It was trained on AI4Bharat's speech corpora for authentic pronunciation and prosody across these languages, which generic multilingual models handle poorly. Built on a Flan-T5 encoder with a MusicGen-style decoder and DAC, and released under Apache 2.0, it fits Indian-language voiceovers and regional content.
Ọkachasị maka: Indian-language voiceovers, regional content, multilingual Indic applications
Nlegharịa niile Indic Parler TTS ụdaN'ime nlele
- Ńkwádò
- AI4Bharat
- Ikikere
- Apache 2.0
- Tier
- standard
- Nhazi
- slow
- Nhazi ụda
- Ọ bụghị
- Asụsụ ndị ahụ
- Tamil, Bengali, Marathi, Gujarati, Kannada, Punjabi, Odia, Assamese, Hindi, Telugu, Malayalam, English
- Ụhara Max
- 500