QuantClarity

Getting Started

Quickstart

Get a transcript in under 2 minutes. You need an API key and an audio file — that's it.

Step 1 — Create an API key

Go to your Dashboard → API Keys and create a new key. Copy it — you won't see it again.

Your key starts with qc_live_. Keep it secret — it grants access to your credits.

Step 2 — Send your audio file

For files under 4 MB, send the audio directly. Replace qc_live_REPLACE_WITH_KEY with your real key and /path/to/audio.mp3 with your file.

terminal
curl https://api.quantclarity.com/v1/audio/transcriptions \
-H "Authorization: Bearer qc_live_REPLACE_WITH_KEY" \
-F "file=@/path/to/audio.mp3" \
-F "model=auto"
File over 4 MB? Use the two-step upload flow — upload to storage first, then pass file_id instead of file.

Step 3 — Read the response

You'll get back a transcription object. The full text is in text, timestamps in segments.

response (200 OK)
{
"id": "tr_01234567-89ab-cdef-0123-456789abcdef",
"status": "completed",
"text": "Your transcribed text appears here.",
"language": { "code": "en", "source": "detected" },
"segments": [
    { "start": 0.0, "end": 3.2, "text": "Your transcribed text" },
    { "start": 3.2, "end": 5.8, "text": "appears here." }
],
"routing": {
    "model": "openai/whisper-large-v3",
    "provider": "openrouter",
    "reason": "table: en → openai/whisper-large-v3"
},
"usage": { "audio_seconds": 60, "credits": 1 },
"error": null
}

Optional — Add a language hint

If you know the language in advance, pass it as a hint. This improves accuracy and picks the best model for that language.

terminal
curl https://api.quantclarity.com/v1/audio/transcriptions \
-H "Authorization: Bearer qc_live_REPLACE_WITH_KEY" \
-F "file=@/path/to/audio.mp3" \
-F "model=auto" \
-F "language=ur"

Supported language codes follow ISO 639-1 (e.g. ar, ur, es, fr, zh). Regional variants like ur-PK are normalized automatically. See the full list of supported language codes.

Next steps