LAION Voice

non-profit

LAION-Voice

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

HarryHe authored a paper 19 days ago

Overview of the Amphion Toolkit (v0.2)

HarryHe authored a paper 19 days ago

Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

gijs authored a paper 27 days ago

Audio-Language Datasets of Scenes and Events: A Survey

View all activity

kadirnar

posted an update 8 days ago

Post

1651

What can you do with the VyvoTTS library?

- You can train a model in a language it has never been trained in using the PT model. There’s no need for large datasets.
- With the PT model, you can easily replicate the voice of any character you want. Just 1k samples are enough.
- You can add emotion support with a small dataset.

Github: https://github.com/Vyvo-Labs/VyvoTTS
HuggingFace:

Vyvo

HarryHe

authored 2 papers 19 days ago

Overview of the Amphion Toolkit (v0.2)

Paper • 2501.15442 • Published Jan 26 • 3

Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

Paper • 2508.06059 • Published 25 days ago • 4

gijs

authored 4 papers 27 days ago

Audio-Language Datasets of Scenes and Events: A Survey

Paper • 2407.06947 • Published Jul 9, 2024

AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound

Paper • 2505.14142 • Published May 20

Data-Balanced Curriculum Learning for Audio Question Answering

Paper • 2507.06815 • Published Jul 9

ACES: Evaluating Automated Audio Captioning Models on the Semantics of Sounds

Paper • 2403.18572 • Published Mar 27, 2024

mrfakename

posted an update 4 months ago

Post

6959

Hi everyone,

I just launched TTS Arena V2 - a platform for benchmarking TTS models by blind A/B testing. The goal is to make it easy to compare quality between open-source and commercial models, including conversational ones.

What's new in V2:

- **Conversational Arena**: Evaluate models like CSM-1B, Dia 1.6B, and PlayDialog in multi-turn settings
- **Personal Leaderboard**: Optional login to see which models you tend to prefer
- **Multi-speaker TTS**: Random voices per generation to reduce speaker bias
- **Performance Upgrade**: Rebuilt from Gradio → Flask. Much faster with fewer failed generations.
- **Keyboard Shortcuts**: Vote entirely via keyboard

Also added models like MegaTTS 3, Cartesia Sonic, and ElevenLabs' full lineup.

I'd love any feedback, feature suggestions, or ideas for models to include.

TTS-AGI/TTS-Arena-V2

7 replies

mrfakename

posted an update 5 months ago

Post

3026

Papla P1 from Papla Media is now available on the TTS Arena!

Try out Papla's new ultra-realistic TTS model + compare it with other leading models on the TTS Arena: TTS-AGI/TTS-Arena

mrfakename

posted an update 6 months ago

Post

2901

GGUF quants (text-only) for the new Mistral Small 3.1 24B are now live:

mrfakename/mistral-small-3.1-24b-instruct-2503-gguf

mrfakename

posted an update 6 months ago

Post

2366

Converted the new Mistral Small 3.1 models to HF format (currently text-only, no vision):

Instruct: mrfakename/mistral-small-3.1-24b-instruct-2503-hf
Base: mrfakename/mistral-small-3.1-24b-base-2503-hf

GGUF quants coming soon!

lmxue

authored 2 papers 6 months ago

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

Paper • 2503.01710 • Published Mar 3 • 6

Audio-FLAN: A Preliminary Release

Paper • 2502.16584 • Published Feb 23 • 37

kadirnar

posted an update 7 months ago

Post

5464

Researchers developed Sonic AI enabling precise facial animation from speech cues 🎧 Decouples head/expression control via audio tone analysis + time-aware fusion for natural long-form synthesis

1 reply

HarryHe

authored 3 papers 7 months ago

Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation

Paper • 2501.15907 • Published Jan 27 • 17

Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation

Paper • 2407.05361 • Published Jul 7, 2024 • 2

SpMis: An Investigation of Synthetic Spoken Misinformation Detection

Paper • 2409.11308 • Published Sep 17, 2024

mrfakename

posted an update 7 months ago

Post

2639

I’m excited to introduce a new leaderboard UI + keyboard shortcuts on the TTS Arena!

The refreshed UI for the leaderboard is smoother and (hopefully) more intuitive. You can now view models based on a simpler win-rate percentage and exclude closed models.

In addition, the TTS Arena now supports keyboard shortcuts. This should make voting much more efficient as you can now vote without clicking anything!

In both the normal Arena and Battle Mode, press "r" to select a random text, Cmd/Ctrl + Enter to synthesize, and "a"/"b" to vote! View more details about keyboard shortcuts by pressing "?" (Shift + /) on the Arena.

Check out all the new updates on the TTS Arena:

TTS-AGI/TTS-Arena

1 reply

kadirnar

posted an update 8 months ago

Post

4463

I created my own AI image and video from scratch using the fal.ai platform 💫

Workflow: Flux Lora Training + Upscale + Kling AI(1.6)

6 replies

mrfakename

posted an update 11 months ago

Post

7858

I just released an unofficial demo for Moonshine ASR!

Moonshine is a fast, efficient, & accurate ASR model released by Useful Sensors. It's designed for on-device inference and licensed under the MIT license!

HF Space (unofficial demo): mrfakename/Moonshine
GitHub repo for Moonshine: https://github.com/usefulsensors/moonshine

AI & ML interests

Recent Activity

Team members 8

LAION-Voice's activity