Full body waifus, AI dreams, realtime AI music, open-source Gemini Omni: AI NEWS
Open TTS model with inline tags to control emotion, style, speed, pitch, pauses and sound effects. Tops other open TTS models in comparisons; 9.3GB on Hugging Face.
Text-to-speech model from Boson AI with inline tags for emotion, style, speed, pitch, pauses and sound effects.
Updated EU status checked Last shown
Higgs Audio v3 at a glance
- What is Higgs Audio v3?
- Higgs Audio v3 is a model from Boson AI. Text-to-speech model from Boson AI with inline tags for emotion, style, speed, pitch, pauses and sound effects.
- Who makes Higgs Audio v3?
- Higgs Audio v3 is made by Boson AI.
- Does Higgs Audio v3 work in the EU?
- Unverified. No explicit evidence found. The pages show no supported-countries list or EU exclusion; the API is self-serve with API keys, and weights are reportedly downloadable. Last verified 14 Nov 2026.
- How much does Higgs Audio v3 cost?
- API pricing. Pay-as-you-go via Boson API: $0.015 per 1K characters for TTS; $10 free trial credit for new accounts. Weights reportedly also downloadable.
- Where was Higgs Audio v3 shown?
- In 1 creator video by AI Search. Most recently by AI Search on 7 Jun 2026, at 43:07 in “Full body waifus, AI dreams, realtime AI music, open-source Gemini Omni: AI NEWS”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
About
Higgs Audio v3 is a text-to-speech model from Boson AI, a company building speech-to-speech models, real-time avatars and production TTS for voice agents. According to a YouTube creator review, it accepts inline tags in the text to control emotion, style, speed, pitch, pauses and sound effects, and a Hugging Face release of about 9.3 GB was mentioned.
Boson's website describes TTS in 100+ languages and an API platform. Billing is per character, with the pricing page listing $0.015 per 1K characters. Characters are counted language-agnostically, and style descriptions are included in the count. New accounts receive $10 in free trial credit.
The provided pages do not confirm the Higgs Audio v3 release date, license, or Hugging Face repository URL, so those fields are left unset. Creator comparisons claiming it outperforms other open TTS models are unverified here.
Key features
- Inline tags for emotion, style, speed, pitch and pauses
- Sound-effect control via tags
- Multilingual production TTS (100+ languages per Boson)
- Per-character API pricing ($0.015 per 1K characters)
- Reportedly open weights on Hugging Face (~9.3 GB)
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.
M3
Ming 3.0 TTS
Model · Ant Group
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
AT
Audio8 TTS 0.1B
Model · Edge0
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
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
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
DO
dots.tts
Model · Rednote
Open-source 2B-parameter zero-shot voice-cloning text-to-speech model from Rednote's hilab team.
Available in EUVoice & Audio
Release date n/aOpen source
DR
DramaBox
Model · Resemble AI
Open-weights expressive text-to-speech model from Resemble AI with voice cloning, fine-tuned from LTX-2.3 audio.
Available in EUVoice & Audio
17 Apr 2026Open source