Audio

Three endpoint groups: speech-to-text, audio translation, and text-to-speech (TTS). Transcription/translation upload files as multipart/form-data; TTS takes JSON and returns binary audio.

Transcriptions

POST /v1/audio/transcriptions

curl https://test.kailin.com.cn/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-your-token" \
  -F "file=@/path/to/audio.mp3" \
  -F "model=whisper-1" \
  -F "language=zh"

Fields (form-data)

Field	Type	Required	Description
file	file	Yes	Audio file (mp3/wav/m4a/webm etc., ≤25MB)
model	string	Yes	whisper-1, gpt-4o-transcribe, gpt-4o-mini-transcribe, etc.
language	string	No	ISO-639-1 code (e.g. zh) — improves accuracy
prompt	string	No	Guiding text to help spell proper nouns
response_format	string	No	json (default) / text / srt / verbose_json / vtt
temperature	number	No	Sampling temperature

Response

{ "text": "This is the transcribed text." }

The verbose_json format additionally returns segments and timestamps (segments / duration).

Translations

POST /v1/audio/translations

Translates audio content into English. Fields are the same as transcriptions (no language parameter):

curl https://test.kailin.com.cn/v1/audio/translations \
  -H "Authorization: Bearer sk-your-token" \
  -F "file=@/path/to/audio.mp3" \
  -F "model=whisper-1"

{ "text": "This is the English translation of the audio." }

Text to Speech

POST /v1/audio/speech

curl https://test.kailin.com.cn/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-token" \
  -d '{
    "model": "tts-1",
    "voice": "alloy",
    "input": "Welcome to AI Station."
  }' \
  --output speech.mp3

Request Body

Parameter	Type	Required	Description
model	string	Yes	tts-1, tts-1-hd, gpt-4o-mini-tts, etc.
input	string	Yes	Text to synthesize — up to 4096 characters
voice	string	Yes	alloy / echo / fable / onyx / nova / shimmer, etc.
response_format	string	No	mp3 (default) / opus / aac / flac / wav / pcm
speed	number	No	0.25–4.0, default 1.0

Response

On success the endpoint returns raw audio bytes (encoded per response_format). Save it as a file instead of parsing it as JSON.

caution

When using the web playground for transcription/translation, switch to the form mode to upload files. The TTS response is a binary stream — the playground embeds an audio player for it, but cURL/SDK validation is recommended.