InterconnectsInterconnects Artifacts Hub
withVAILVAIL
All models

S1-mini

byfishaudiofishaudio· 31 May 2025
Audio generation

A non-commercial text-to-speech model trained on over 2 million hours of multilingual audio data with support for emotional and tone markers.

Specs
Params0.5B
LicenseCC-BY-NC-SA-4.0
Tags
models/audio-generationmultilingual
Resources
Hugging Face — fishaudio/s1-miniAppeared in Artifacts Log #11
How these metrics work
Adoption · Hugging Face
RAM score
Relative Adoption Metric not applicable.
Hugging Face Downloads
2.1K
last 30d
109.7K
all time
HF Likes
786

Relative Adoption Metric not applicable.

Related Models

More from fishaudio

Drama 3
fishaudiofishaudio01 Oct 2026

Similar Models

OuteTTS-1.0-0.6B
OuteAIOuteAI18 May 2025
audio generation600M params
Spark-TTS-0.5B
SparkAudioSparkAudio27 Feb 2025
audio generation500M params
VoxCPM-0.5B
OpenBMBOpenBMB16 Sep 2025
audio generation500M params
LLaMA-Omni 2
ICTNLPICTNLP15 Apr 2025
audio generation500M params