Bark Small TTS
A distilled 150M version of Suno's Bark that trades some fidelity for roughly twice the speed and half the memory.
Ojehaijey ñe'ẽnguéra etiquetas SSML-pe peteĩ control hekopete g̃uarã:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Etiquetas ohechakuaáva modelo ojeporavóva - tesãirã peteĩ peteĩva ñe'ẽnguérape, oĩhápe:
Ko modelo ohai texto ndahasyivéva, upévare umi etiqueta oĩva línea ryepýpe ndojehechakuaái. Umi emoción oñemopyendáva etiqueta-pe g̃uarã, oñemoambue peteĩ modelo expresivo-pe taha'e Orfeo térã Bark.
Oñemohenda ñe'ẽnguéra ojehechapyréva (tembiapo = ñe'ẽnguéra):
Mba'épa Bark Small
Bark Small is Suno's distilled, lightweight take on Bark, shrinking the model to 150M parameters. It keeps Bark's signature ability to produce emotional speech, laughter, and multilingual output across the same 13+ languages, but generates noticeably faster (~8s versus ~15s) and fits in about 2GB of VRAM. The cost is some audio quality, so it works best as the go-to when full Bark is too slow for a creative task but you still want its expressive, sound-rich character. Like full Bark it caps at 200 characters per generation and does not support voice cloning.
Oñeha'ãvéva: Quick creative audio when full Bark is too slow
Ojehecha opavave Bark Small ñe'ẽPeteĩ jehecha
- Desarrollador
- Suno
- Licencia
- MIT
- Ta'ãnga
- standard
- Velocidad
- medium
- Clonación ñe'ẽnguéra rehe
- No
- Ñe'ẽ
- English, Chinese, French, German, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, Turkish
- Caracteres máx.
- 200