Speech-to-Text (STT)

curl -X POST https://api.core.today/v1/predictions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
    "model": "openai/whisper-1",
    "input": {
      "audio": "https://example.com/meeting.mp3",
      "response_format": "verbose_json",
      "timestamp_granularities": ["segment"]
    }
  }'

# → {"job_id": "...", "status": "processing", ...}
curl https://api.core.today/v1/predictions/{job_id} -H "X-API-Key: cdt_your_api_key"

{
  "job_id": "91bGtKlfdpgiXxOKVQV6W9pb6r0oYwrD",
  "status": "completed",
  "result": {
    "task": "transcribe",
    "language": "english",
    "duration": 52.41,
    "text": "The little tales they tell are false. ...",
    "segments": [
      { "id": 0, "start": 0.0, "end": 5.04, "text": " The little tales they tell are false." }
    ],
    "usage": { "type": "duration", "seconds": 53 }
  },
  "credits_used": 13
}

curl -X POST https://api.core.today/v1/predictions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
    "model": "openai/whisper",
    "input": {
      "audio": "https://example.com/meeting.mp3",
      "transcription": "srt",
      "language": "auto"
    }
  }'

curl -X POST https://api.core.today/v1/predictions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
    "model": "meta/muse-voice-transcribe-1.0",
    "input": {
      "audio": "https://example.com/meeting.m4a",
      "mode": "DIARIZATION",
      "language_bias": ["Korean", "English"]
    }
  }'

{
  "model": "meta/muse-voice-transcribe-1.0/realtime",
  "audioEncoding": "PCM_24KHZ",
  "mode": "ENDPOINTING",
  "partialMode": "CUMULATIVE",
  "emitAudioProgress": false,
  "keywords": ["Core.Today"],
  "languageBias": ["Korean"],
  "apiKey": "cdt_your_api_key",
  "customerId": "member-123"
}

{"type":"session","sessionId":"rt_..."}
{"type":"transcript","transcript":"...","final":false}
{"type":"usage","sessionId":"rt_...","audioSeconds":73,"credits":9,"reason":"client_end"}

import asyncio, json, os, wave, websockets

API_KEY = os.environ["AIAPI_API_KEY"]
ENDPOINT = "wss://api.core.today/v1/realtime/asr"

async def main():
    async with websockets.connect(
        ENDPOINT, additional_headers={"X-API-Key": API_KEY}
    ) as ws:
        await ws.send(json.dumps({
            "model": "meta/muse-voice-transcribe-1.0/realtime",
            "audioEncoding": "PCM_24KHZ",
            "mode": "ENDPOINTING",
            "languageBias": ["Korean"],
        }))

        async def send_audio():
            with wave.open("meeting-24khz-mono.wav", "rb") as wav:
                frame_bytes = int(24000 * 2 * 0.08)  # 80ms of 16-bit mono PCM
                while chunk := wav.readframes(frame_bytes // 2):
                    await ws.send(chunk)
                    await asyncio.sleep(0.08)  # pace at 1x — never send ahead
            await ws.send(json.dumps({"type": "endStream"}))

        async def recv_events():
            async for msg in ws:
                if isinstance(msg, str):
                    print(json.loads(msg))

        await asyncio.gather(send_audio(), recv_events())

asyncio.run(main())

from openai import OpenAI

client = OpenAI(
    base_url="https://api.core.today/llm/openai/v1",
    api_key="cdt_your_api_key",
)

# gpt-transcribe: text + detected languages (no timestamps)
with open("meeting.mp3", "rb") as f:
    result = client.audio.transcriptions.create(
        model="gpt-transcribe",
        file=f,
        languages=["ko"],  # openai>=3.x; older SDKs: extra_body={"languages": ["ko"]}
        keywords=["Core.Today"],
    )
print(result.text)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.core.today/llm/openai/v1",
    api_key="cdt_your_api_key",
)

with open("meeting.mp3", "rb") as f:
    result = client.audio.transcriptions.create(
        model="whisper-1",
        file=f,
        response_format="verbose_json",
        timestamp_granularities=["segment"],
    )

print(result.text)
for seg in result.segments:
    print(seg.start, seg.end, seg.text)

curl https://api.core.today/llm/openai/v1/audio/transcriptions \
  -H "Authorization: Bearer cdt_your_api_key" \
  -F file=@meeting.mp3 \
  -F model=gpt-transcribe \
  -F "languages[]=ko"