Skip to content

Wizper (Whisper v3)

Integrate

Model id wizper
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/wizper?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Up to $1.998 per run charged by actual usage, the rest is refunded Run it on this page

Get API key
OpenAI Speech to Text #transcription#speech

Whisper v3 speech transcription and translation to English with timestamped chunks

OpenAI · Text

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required audio_url
Drop a file, or

Transcription input supplied as a URL pointing to an audio file in mp3, mp4, mpeg, mpga, m4a, wav or webm format.

Advanced task · language · chunk_level · version · max_segment_len · merge_chunks
task default transcribe

Audio processing task: choose transcribe or translate.

default en

Audio language selection, with `None` requesting automatic detection at the expense of longer inference time. For the translate task, English is always the translation target, so this language selection does not change the output language.

default segment

Granularity of the returned chunks.

default 3

Version selection within the Whisper large family; no other Whisper variant is used by these models.

default 29

Speech segment length limit, measured in seconds, after which splitting occurs.

POST /run/wizper?wait=20 quote → $1.998
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/wizper?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Wizper (Whisper v3)

Transcribes an audio file from a URL (mp3, mp4, mpeg, mpga, m4a, wav or webm), or translates it to English with `task`. The `language` field supports 99 values, and automatic detection is possible. Returns the full text plus timestamped chunks. `max_segment_len` (10-29 seconds) and `merge_chunks` control how segments are split.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
audio_urlrequired audio
Typeurl · audio
Transcription input supplied as a URL pointing to an audio file in mp3, mp4, mpeg, mpga, m4a, wav or webm format.
taskoptional
Typeenum
Defaulttranscribe
transcribetranslate
Audio processing task: choose transcribe or translate.
languageoptional
Typeenum
Defaulten
afamarasazbabebgbnbobrbscacscyda
+83 moredeeleneseteufafifofrglguhahawhehihrhthuhyidisitjajwkakkkmknkolalblnloltlvmgmimkmlmnmrmsmtmynenlnnnoocpaplpsptrorusasdsiskslsnsosqsrsusvswtatetgthtktltrttukuruzviyiyozh
Audio language selection, with `None` requesting automatic detection at the expense of longer inference time. For the translate task, English is always the translation target, so this language selection does not change the output language.
chunk_leveloptional
Typestring
Defaultsegment
Granularity of the returned chunks.
max_segment_lenoptional
Typeinteger
Default29
10 – 29
Speech segment length limit, measured in seconds, after which splitting occurs.
merge_chunksoptional
Typeboolean
Defaulttrue
Consecutive-chunk merging control, permitting a merge only if the resulting segment's duration is no greater than max_segment_len.
versionoptional
Typestring
Default3
Version selection within the Whisper large family; no other Whisper variant is used by these models.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "wizper",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1998,
    "usd": "1.998",
    "charged": 1998,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "text": "string",
    "chunks": [
      {
        "timestamp": [],
        "text": "string"
      }
    ],
    "languages": [
      "af"
    ]
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
text
stringText transcribed from the audio.
chunks
array of object {timestamp, text}Audio chunks accompanied by timestamps.
languages
array of enum (string)Audio language-detection results, returned as a list of inferred languages with null as the default value.

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/wizper.md. All models and guides: https://doitong.com/developers/llms.txt