All models
controllable

Parler-TTS

Apache-2.0

Describe the voice in natural language ('soft female, fast, clear')

Parler-TTS, from Hugging Face's audio team, takes a different approach: instead of cloning a reference, you describe the speaker in text — "a calm female voice with a slight British accent, speaking slowly" — and it synthesizes that voice. Fully open training code and data recipes.

Voices

5 voices
Female
Clear female, calmdefault
american
Warm female, expressive
british
Male
Deep male, confident
american
Newscaster, formal
american
Friendly male, casual
american

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

pip install parler-tts

Parler-TTS FAQ

Do I need a GPU to run Parler-TTS?

For practical speeds, yes — plan on roughly 6 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can Parler-TTS clone voices?

No — Parler-TTS uses preset voices. Browse the voice-cloning category for models that clone from reference audio.

What license is Parler-TTS released under?

Parler-TTS is released under the Apache-2.0 license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does Parler-TTS support?

Parler-TTS supports English.

Is there a hosted Parler-TTS API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to Parler-TTS and every other model in this directory. No CUDA, Docker, or GPU needed.