Parler-TTS Large v1
Key facts · verified Oct 27, 2026
Parler-TTS Large v1 is a Hugging Face audio generation model released on 8 Aug 2024. Pricing: Open weights - free to self-host. Source: huggingface.co.
Parler-TTS Large v1 is an open-weight text-to-speech model from Hugging Face's Parler-TTS project, published on Hugging Face on August 8, 2024 under the Apache 2.0 licence. The model card describes a 2.2-billion-parameter model trained on 45,000 hours of English audio, with speaker gender, pitch, speaking rate, background noise and reverberation set through a plain-text description, and 34 named speakers for a consistent voice across prompts. Hugging Face published it alongside Parler-TTS Mini v1 as the project's second set of models.
Open weights - free to self-host
Not published
Not rated
Not ranked
Key Features
Full Specifications
Open weights - free to self-host | |
|---|---|
| Identity | |
| Developer | Hugging Face |
| Released | Aug 2024 |
| Status | Open weights |
| Licence | Apache 2.0 |
| Self-hostable | Yes |
| Cost | |
| Price per minute | Free — open weights, self-hosted |
| Capability | |
| Voice cloning | No — 34 named speakers, voice described in plain text |
| Languages | English |
| Access | |
| Fine-tuning | Yes — training code and datasets are published |