Deprecated model — this model still works, but we recommend a newer model for new projects.

Billing note OpenAI shuts whisper-1 down on 2027-02-26 - move to openai/gpt-transcribe (no timestamps) or, for segment timestamps, openai/whisper (Replicate). Billing is per second of audio. 840 credits (the 1-hour maximum) are reserved when the job starts - or the file's actual length when it is a WAV/MP3/MP4/M4A whose header can be read - and the difference is refunded once OpenAI reports the measured duration.

OpenAIDeprecatedFastHigh

Whisper-1 (OpenAI API)

OpenAI's hosted whisper-1 speech recognition with the OpenAI API parameters - json or verbose_json output, segment and word timestamps (timestamp_granularities), language hint and prompt. Billed per second of audio (0.2325 credits/s, about 14 credits per minute), up to 1 hour / 25MB per request.

840 credits

per minute of audio (0.2325/s, settled on measured length)

OpenAI's hosted whisper-1 with the OpenAI API parameter names

verbose_json output with language, duration and timestamped segments

Segment and word timestamps via timestamp_granularities

~100 languages with auto detection, or an ISO-639-1 language hint

Accepts flac, m4a, mp3, mp4, mpeg, mpga, ogg, wav and webm up to 25MB

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

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://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav",
    "response_format": "verbose_json",
    "timestamp_granularities": [
      "segment"
    ],
    "language": "en"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`audio`	string	Yes	-	Audio file URL (flac, m4a, mp3, mp4, mpeg, mpga, ogg, wav, webm). Sent to OpenAI as the `file` part. Max 25MB and 1 hour.
`response_format`	string	No	json	json returns {text, usage}; verbose_json adds language, duration and timestamped segments/words. text, srt and vtt are not available through this API. jsonverbose_json
`timestamp_granularities`	array	No	-	Timestamp detail for verbose_json - segment, word or both. Requires response_format verbose_json. Word timestamps add latency; segment timestamps add none. segmentword
`language`	string	No	-	Language of the input audio as an ISO-639-1 code (e.g. ko, en, ja). Improves accuracy and latency. Omit for automatic detection.
`prompt`	string	No	-	Optional text to guide style or continue a previous segment. Should match the audio language.
`temperature`	number	No	0	Sampling temperature between 0 and 1. 0 lets the model raise it automatically until certain thresholds are hit.

How to Provide File Input

There are 3 ways to provide files for the audio parameter:

Recommended

Image URL

Pass a publicly accessible URL directly. With the Storage API (POST /v1/files/upload-url) the file uploads straight to S3 (50MB per file) and you pass the returned file_url.

{
  "model": "openai/whisper-1",
  "input": {
    "prompt": "your prompt here",
    "audio": "https://example.com/image.jpg"
  }
}

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step, but the bytes pass through the API server so the whole request is capped at 10MB.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=openai/whisper-1" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:audio=@your_file.png"

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Segment timestamps (verbose_json)

Returns text, language, duration and segments with start/end seconds.

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://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav",
    "response_format": "verbose_json",
    "timestamp_granularities": [
      "segment"
    ],
    "language": "en"
  }
}'

Plain transcript (json)

Returns {text, usage} for a Korean recording.

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.m4a",
    "response_format": "json",
    "language": "ko"
  }
}'

Tips & Best Practices

1Retiring: OpenAI shuts whisper-1 down on 2027-02-26 (the translations endpoint too). openai/gpt-transcribe is the replacement for plain transcripts and is cheaper; it has no timestamps, so keep timestamp workflows on openai/whisper (Replicate segments)

2The result is OpenAI's response body as-is: json gives text and usage.seconds (the billed length); verbose_json gives text, language, duration and segments/words

3timestamp_granularities works only with verbose_json; when omitted, verbose_json returns segment timestamps

4Split files over 25MB or 1 hour before submitting - longer or larger files are rejected

5For SRT/VTT subtitles, build them from verbose_json segments, or use openai/whisper (Replicate) which outputs srt/vtt directly

6OpenAI SDK: point the client at base_url https://api.core.today/llm/openai/v1 with your cdt_ API key and call client.audio.transcriptions.create(model="whisper-1", file=..., response_format="verbose_json", timestamp_granularities=["segment"]) - the file is uploaded directly (no URL), json/verbose_json only, billed per second at the LLM rate (0.1858 credits/s, about 11.15 per minute) on the length OpenAI reports