Audio Transcription
Speech to text for any audio or video URL, with speaker labels and word timestamps.
curl -X POST https://api.1lookup.dev/v1/audio-transcription \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"audio_url":"https://files.example.com/calls/2026-11-02-discovery.mp3","speakers":"on"}'{
"success": true,
"data": {
"audio_url": "https://files.example.com/calls/2026-11-02-discovery.mp3",
"language": "en",
"duration_seconds": 1260,
"speaker_count": 2,
"text": "Thanks for joining, Priya. Can you walk me through how inbound leads are handled today? Sure. Every form fill lands in a shared inbox, and someone calls the number by hand.",
"segments": [
{
"speaker": "A",
"start": 0.48,
"end": 5.12,
"text": "Thanks for joining, Priya. Can you walk me through how inbound leads are handled today?"
},
{
"speaker": "B",
"start": 5.74,
"end": 11.3,
"text": "Sure. Every form fill lands in a shared inbox, and someone calls the number by hand."
}
],
"words": [
{
"word": "Thanks",
"start": 0.48,
"end": 0.81,
"speaker": "A"
},
{
"word": "for",
"start": 0.81,
"end": 0.95,
"speaker": "A"
},
{
"word": "joining,",
"start": 0.95,
"end": 1.42,
"speaker": "A"
},
{
"word": "Priya.",
"start": 1.47,
"end": 1.98,
"speaker": "A"
}
]
},
"meta": {
"credits_used": 6,
"credits_remaining": 999,
"cached": false,
"request_id": "req_8f3a2c1e9b7d"
}
}Authorization
Authorizationstring<bearer>requiredYour API key as a Bearer token. Live keys start with 1lk_live_. Test keys start with 1lk_test_ and return this endpoint's sample response without spending credits. See authentication.
Body
Send the fields as a JSON object with Content-Type: application/json.
audio_urlstring<uri>requiredAudio or video URL. Example: https://files.example.com/calls/2026-11-02-discovery.mp3
speakersenum<string>requiredSpeaker labels. One of: on, off. Example: on
freshbooleanSkip the 7-day cache and run a new lookup. Charged as a normal lookup.
referencestringYour own identifier, echoed back in meta and shown in lookup history.
Response
A 200 response carries the result in data and the cost of the call in meta. These are the fields most integrations read.
successbooleantrue when the lookup ran.
data.textstringThe full transcript as a single string.
data.segmentsarrayThe transcript split into turns, each with a speaker label and start and end times.
data.wordsarrayEvery word with its start and end time in seconds.
data.languagestringThe language code identified from the audio.
data.speaker_countnumberHow many distinct speakers were heard.
data.duration_secondsnumberLength of the audio, which is what billing is based on.
meta.credits_usednumberCredits charged for this call.
meta.credits_remainingnumberYour balance after the call.
meta.cachedbooleantrue when the result came from the 7-day cache.
meta.request_idstringQuote this when you contact support.
Errors
A failed request returns success: false with an error object, and is never charged. The full list is on the errors page.
| HTTP | Code | Meaning |
|---|---|---|
| 401 | unauthorized | The key is missing, malformed or revoked. |
| 402 | insufficient_credits | Your credits are used up and pay as you go is off or at its limit. |
| 422 | invalid_input | A field is missing or malformed. The field property names it. |
| 429 | rate_limited | Too many requests for this key. Wait for the Retry-After interval. |
| 500 | internal_error | Something failed on our side. Safe to retry. |
| 503 | source_unavailable | An upstream source did not answer in time. Safe to retry. |
Billing
6 credits / minute. Charged when the lookup runs and returns a result. Errors are never charged, and repeating the same input within 7 days is served from cache at no charge.
Product overview and use cases