跳到主要内容

音频​格式​与​语言

Shisa ASR ​接受​多​种​常见​格式​的​ base64 ​编码​音频,​并​跨9​7​种​语言​自动识别所​说​的​语言。​本页列​出​支持​的​格式,​演示​如何​将​音​频​编码​为​ base​64,​并​介绍​语言​检测。

支持​的​音频​格式

将​原始​的​ base64 ​编码​音频数​据​传入​ audio ​字段。​服务器​会​从​二进制头​自动​检测​格式​——​您​无​需​自行声明​格式。

FormatMIME typeDetection
WAVaudio/wavRIFF header
OGGaudio/oggOggS header
MP3audio/mpegID3 tag or MPEG sync bytes
FLACaudio/flacfLaC header

将​音频​编码​为​ base64

将​任何​受​支持​的​文件​转换​为​ base​64,​然后​将​其​直接​嵌入​您​的​请求​中:

# Encode any supported format to base64
base64 -w0 audio.ogg # Linux
base64 -i audio.ogg # macOS

# Use in a curl request
curl -s -XPOST 'https://api.shisa.ai/asr/srt/audio_llm' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{ "audio": "'$(base64 -w0 audio.ogg)'" }'

语言​检测​(LID)

API ​支持​跨9​7​种​语言​的​自动​语​言识别​(LID)。​当​您​省​略 language ​参数​时,​所说​的​语言​会​被​自动​检测,​并​在​响应​的​ language ​字段​中​返回。​要​强制​使用​特定​语言,​请​显式​设置​ language(例如​ "ja" ​或​ "en")。

主要​语言

CodeLanguage
jaJapanese
enEnglish
zhChinese
全部​9​7​种​支持​的​语言
CodeLanguage
afAfrikaans
amAmharic
arArabic
asAssamese
azAzerbaijani
baBashkir
beBelarusian
bgBulgarian
bnBengali
boTibetan
brBreton
bsBosnian
caCatalan
csCzech
cyWelsh
daDanish
deGerman
elGreek
enEnglish
esSpanish
etEstonian
euBasque
faPersian
fiFinnish
foFaroese
frFrench
glGalician
guGujarati
haHausa
hawHawaiian
heHebrew
hiHindi
hrCroatian
htHaitian Creole
huHungarian
hyArmenian
idIndonesian
isIcelandic
itItalian
jaJapanese
jwJavanese
kaGeorgian
kkKazakh
kmKhmer
knKannada
koKorean
laLatin
lbLuxembourgish
lnLingala
loLao
ltLithuanian
lvLatvian
mgMalagasy
miMaori
mkMacedonian
mlMalayalam
mnMongolian
mrMarathi
msMalay
mtMaltese
myMyanmar
neNepali
nlDutch
nnNorwegian Nynorsk
noNorwegian
ocOccitan
paPunjabi
plPolish
psPashto
ptPortuguese
roRomanian
ruRussian
saSanskrit
sdSindhi
siSinhala
skSlovak
slSlovenian
snShona
soSomali
sqAlbanian
srSerbian
suSundanese
svSwedish
swSwahili
taTamil
teTelugu
tgTajik
thThai
tkTurkmen
tlTagalog
trTurkish
ttTatar
ukUkrainian
urUrdu
uzUzbek
viVietnamese
yiYiddish
yoYoruba
zhChinese

后续​步​骤