Parler TTS

Parler TTS TTS

Describe the voice you want in plain English and Parler generates speech matching that description.

Sign up for 5,000 character limit

Wrap your text in SSML tags for precise control:

<speak><prosody rate="slow">Slow speech</prosody></speak>

Tags the selected model understands — click to drop one into your text where it happens:

This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.

Define custom pronunciations (word = pronunciation):

-12 +12
0.5x 2.0x
Free with Piper, VITS, MeloTTS
Your generated audio will appear here. Choose a model, enter text, and click Generate.
Audio Generated Successfully
0:00
Download Audio Download .srt Link expires in 24h
Free tier: personal use. Commercial license from $5/mo
Love TTS.ai? Tell your friends!

About Parler TTS

Parler TTS, developed by Hugging Face, replaces voice presets with natural-language control: instead of picking from a fixed list, you write a description such as "a warm female voice with a slight British accent, speaking slowly and clearly," and the model synthesizes speech to match. This makes it unusually flexible for creative work where you need a specific, custom voice character without recording or cloning anyone. It is an 880M-parameter transformer encoder-decoder trained on roughly 45,000 hours of speech, and it is released under the permissive Apache 2.0 license. Parler is English-focused and best suited to applications that benefit from on-demand, describable voice characteristics.

Best for: Creative applications where you need custom voice characteristics

Browse all Parler TTS voices

At a glance

Developer
Hugging Face
License
Apache 2.0
Tier
standard
Speed
medium
Voice cloning
No
Languages
English
Max characters
500

Parler TTS voices

Default

English
Standard Neutral

Parler TTS TTS — FAQ

You describe it in natural language — gender, accent, pace, tone, and recording quality — and Parler generates speech matching the description. There are no preset voices to choose from.

Hugging Face. It is an 880M-parameter transformer encoder-decoder trained on around 45,000 hours of speech and released under Apache 2.0.

No. Parler generates a voice from a text description rather than from a reference recording. For cloning a specific voice, use a model like Chatterbox or GPT-SoVITS.
← All voices