Parler-TTS

Prompt-controllable speech: describe the voice you want in plain English.

When to use it

Use this when you need to steer pitch, pace and accent through a text prompt rather than pick from a fixed speaker list.

Text-to-speech, speech-to-text and audio models under one MLX package.

A batched, quantized Whisper reimplementation chasing raw transcription speed.

Speech in, speech out, skipping the ASR-LLM-TTS relay race.