Skip to content
latestai.eulatestai.eu
DO

dots.tts

by Rednote

Open-source 2B-parameter zero-shot voice-cloning text-to-speech model from Rednote's hilab team.

Available in EUVoice & AudioModel

Updated EU status checked Last shown

dots.tts at a glance

What is dots.tts?
dots.tts is a model from Rednote. Open-source 2B-parameter zero-shot voice-cloning text-to-speech model from Rednote's hilab team.
Who makes dots.tts?
dots.tts is made by Rednote.
Does dots.tts work in the EU?
Available in the EU. Reported as Apache 2.0 open weights, which carry no geographic restriction, so it should be usable in the EU; no explicit EU-specific evidence was found. Last verified 14 Nov 2026.
How much does dots.tts cost?
Open source, open source. Reported as free open-source weights under Apache 2.0; no hosted pricing known. Licence: Apache-2.0.
Where was dots.tts shown?
In 1 creator video by AI Search. Most recently by AI Search on 14 Jun 2026, at 24:48 in “RIP Claude Fable, open-source AI unleashed, full body avatars, new Google models, new TTS: AI NEWS”.

Sources: creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.

About

dots.tts is a text-to-speech model from Rednote (Xiaohongshu) hilab. According to a creator review, it has about 2 billion parameters and supports zero-shot voice cloning, producing speech in a new voice from a short reference sample without fine-tuning.

The same review says it handles non-standard speech such as stuttering and whispering, supports multiple languages, and reports lower error rates and higher speaker similarity than recent open TTS models such as CosyVoice. These benchmark claims come from the creator's summary and were not verified against an official page.

It is reported to be released under Apache 2.0. A demo page exists at the project's GitHub Pages site. Repository, weights and paper links were not available when this entry was written, so details on hardware requirements, supported languages and exact release date are unconfirmed.

Key features
  • About 2B parameters
  • Zero-shot voice cloning from a reference sample
  • Handles stuttering and whispering
  • Multilingual speech synthesis
  • Reported Apache 2.0 license
1 moment

As seen on YouTube

Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.

Keep exploring

Similar AI tools

Closest neighbours by meaning, not just by category.

AT

Audio8 TTS 0.1B

Model · Edge0

1

Open-weights 0.17B-parameter multilingual text-to-speech model with zero-shot voice cloning, runs on CPU via ONNX.

Available in EUVoice & Audio
19 Aug 2026Open source
AT

Audio8 TTS Realistic 0.6B

Model

1

Compact 0.6B open text-to-speech model with zero-shot voice cloning and support for 23 languages.

Available in EUVoice & Audio
Release date n/aOpen source
IT

Index TTS 2.5

Model · IndexTeam

1

Open-weights zero-shot text-to-speech model from Bilibili's IndexTeam with voice cloning and emotion control in 5 languages.

Available in EUVoice & Audio
10 Aug 2026Open source
WA

WavTTS

Model · ByteDance

1

Research zero-shot TTS model that generates speech by modeling raw waveforms directly with flow-matching DiT.

UnverifiedVoice & Audio
Release date n/a
M3

Ming 3.0 TTS

Model · Ant Group

1

Open-weights text-to-speech models from Ant Group's Inclusion AI with voice design, cloning and tag-based control.

Available in EUVoice & Audio
Release date n/aOpen source
SA

Scenema Audio

Model

1

Expressive text-to-speech model with zero-shot voice cloning, derived from the LTX 2.3 audio model.

Available in EUVoice & Audio
Release date n/aFreemium