OpenAudio S1
OpenAudio S1 is a text to speech model that generates natural human speech from text, with native support for emotional tones, vocal styles, and non speech sounds like laughing or sighing. It supports 13 languages and comes in two sizes, a 4B parameter flagship model and a 0.5B mini version, with very low word and character error rates.
- Type
- Multimodal
- Weights
- Closed
- Downloads
- 65
Model hub
niobures/OpenAudio-S1
- Repo
- niobures/OpenAudio-S1
- Access
- Public
Technical tags and languages
More from Fish Audio
7
-
977 DL
Fish Audio S2
Audio
Fish Audio S2 is Fish Audio’s latest text-to-speech model designed for natural, emotionally rich speech gener…
-
Fish Audio STT
Multimodal
Fish Audio Speech-to-Text is Fish Audio’s transcription model and tool for podcasts, interviews, and conversa…
-
Fish Speech
Audio
Fish-Speech is an open multilingual text-to-speech system that uses large language models for linguistic unde…
-
S2.1 Pro
Audio
S2.1 Pro is a neural text to speech model that converts text into speech across 83 languages with automatic l…
About Fish Audio
1
Fish Audio is a generative-AI voice platform providing ultra-low-latency text-to-speech, voice cloning and speech-to-text, hosting a library of 2M+ voices via its Fish Audio S2 model.