오디오 (Audio)

​

소개

• OpenAI 형식: /v1/audio/speech(TTS), /v1/audio/transcriptions(STT), /v1/audio/translations — OpenAI Audio API와 호환
• Gemini 네이티브 형식: POST /v1beta/models/{model}:generateContent에 responseModalities: ["AUDIO"] 및 speechConfig 설정(예: gemini-2.5-flash-preview-tts)

​

인증

​

요청 예제

curl -X POST "https://api.gravitex.ai/v1/audio/speech" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello from GravitexAI.",
    "voice": "alloy",
    "response_format": "mp3"
  }' \
  --output speech.mp3

curl -X POST "https://api.gravitex.ai/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

curl -X POST "https://api.gravitex.ai/v1/audio/translations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -F file="@audio.mp3" \
  -F model="whisper-1"

curl -X POST "https://api.gravitex.ai/v1beta/models/gemini-2.5-flash-preview-tts:generateContent" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {"text": "Say cheerfully: Have a wonderful day!"}
        ]
      }
    ],
    "generationConfig": {
      "responseModalities": ["AUDIO"],
      "speechConfig": {
        "voiceConfig": {
          "prebuiltVoiceConfig": {
            "voiceName": "Kore"
          }
        }
      }
    }
  }'

echo "<base64_data>" | base64 --decode > out.pcm

​

공통 매개변수

​

OpenAI 형식

• model: 예: tts-1, tts-1-hd
• input: 읽을 텍스트(최대 4096자)
• voice: alloy, echo, fable, onyx, nova, shimmer

• file: 오디오 파일(multipart)
• model: 예: whisper-1

​

Gemini 형식 (TTS)

• model(경로): 예: gemini-2.5-flash-preview-tts, gemini-2.5-pro-preview-tts
• contents[].parts[].text: 텍스트 또는 스타일 지시
• generationConfig.responseModalities: "AUDIO" 포함 필수
• generationConfig.speechConfig.voiceConfig.prebuiltVoiceConfig.voiceName: 예: Kore, Puck, Charon

• OpenAI Audio API
• Gemini speech generation