Indic Parler-TTS
Indic Parler-TTS is a collaboration between AI4Bharat and the Hugging Face audio team. It fine-tunes the pretrained Indic Parler model on 1,806 hours of speech.
Restricted access
Voice descriptions differ from audio-reference prompting
The model accepts a transcript and a description of the desired speaker or delivery. It also supports named speakers. Its current card recommends Indic-Speak for newer applications without withdrawing the earlier weights.Indic Parler-TTS official model card
Hold the description steady when comparing texts
Practical guidance. Changing both the content and the voice description makes pronunciation differences harder to diagnose. Start with a fixed description, then vary pace or expression.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Restricted access |
| Access | Downloadable |
| Model identifiers | indic-parler-tts |
| Coverage | English and 20 Indian languages listed in the card.Indic Parler-TTS official model card |
| Ancestry | Indic extension of Parler-TTS Mini.Indic Parler-TTS official model card |
| License | Apache 2.0; gated download.Indic Parler-TTS official model card |
Related models
Dehvali Bhili speech model fine-tuned from Indic Parler-TTS on ten hours of studio recordings.
Launch date not confirmedDownloadable- Indic Parler-TTS Pretrained
AI4Bharat · Indic Parler-TTS
Pretrained Indic Parler speech model trained on 8,385 hours of multilingual audio.
Launch date not confirmedRestricted accessDownloadable Speech-generation model for 11 Indian languages using text, reference audio and its transcript.
Launch date not confirmedRestricted accessDownloadable