Chatterbox TTS
Ultra-fast text-to-speech with emotion control and voice cloning.
Chatterbox generates speech with expressive emotion control. Adjust exaggeration and CFG to go from calm narration to dramatic delivery. 9 built-in voices plus zero-shot voice cloning from any audio sample. High-quality 48kHz output option. Open source, fast generation.
Try these prompts
How it works
Describe your vision
Type a detailed prompt or upload a reference sketch, photo, or mood board.
Choose your settings
Pick your resolution and aspect ratio. See the credit cost before you generate.
Generate in seconds
Your image is delivered in seconds. Download, iterate, or pipe into video.
Ready to create with Chatterbox TTS?
Jump into the Studio and start generating. Plans from £10/month.
Choose a PlanExpressive speech with emotion control
Most TTS models produce neutral, even-toned speech. Chatterbox gives you control over emotion intensity. The exaggeration parameter (0.25 to 2.0) controls how dramatic the delivery is. Low values produce calm, professional narration. High values produce animated, emphatic speech. The CFG parameter fine-tunes how closely the output follows the voice characteristics.
Nine built-in voices cover the range from warm and approachable to sharp and authoritative. For custom voices, upload any audio sample and Chatterbox generates speech in that voice. Zero-shot cloning means no training required. Upload a 10-second clip, get speech in that voice immediately.
Output at 24kHz standard or 48kHz high quality. The high-quality option takes slightly longer but produces noticeably richer, more natural output. Chatterbox is the most cost-effective expressive TTS option in the roster.
Emotion, not just words
Exaggeration controls emotional intensity. CFG controls voice adherence. Together they let you dial in exactly the tone you need: enthusiastic product launch, sombre memorial, excited social content, measured technical walkthrough.
Voice cloning from any sample
Upload a short audio clip and generate speech in that voice. No training, no waiting. Use it for consistent character voices across a series, matching a brand spokesperson, or maintaining voice continuity across project phases.
Questions about Chatterbox TTS.
Why Stensyl?
A small indie studio building creative tools the way they should be built. No VC theatre, no funnel games, no faceless support.
Ready to create with Chatterbox TTS?
Professional audio generation. Plans from £10/month.