Skip to main content
Endpoint: POST https://fal.run/fal-ai/whisper Endpoint ID: fal-ai/whisper

Try it in the Playground

Run this model interactively with your own prompts.

​
Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/whisper",
    arguments={
        "audio_url": "https://storage.googleapis.com/falserverless/model_tests/whisper/dinner_conversation.mp3"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

​
Capabilities

  • Audio input
  • Text prompt input

​
API Reference

​
Input Schema

​
audio_url
string
required
URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm.
​
task
TaskEnum
default:"transcribe"
Task to perform on the audio file. Either transcribe or translate. Default value: "transcribe"Possible values: transcribe, translate
​
language
Enum
Language of the audio file. If set to null, the language will be automatically detected. Defaults to null.If translate is selected as the task, the audio will be translated to English, regardless of the language selected.Possible values: af, am, ar, as, az, ba, be, bg, bn, bo, br, bs, ca, cs, cy, da, de, el, en, es, et, eu, fa, fi, fo, fr, gl, gu, ha, haw, he, hi, hr, ht, hu, hy, id, is, it, ja, jw, ka, kk, km, kn, ko, la, lb, ln, lo, lt, lv, mg, mi, mk, ml, mn, mr, ms, mt, my, ne, nl, nn, no, oc, pa, pl, ps, pt, ro, ru, sa, sd, si, sk, sl, sn, so, sq, sr, su, sv, sw, ta, te, tg, th, tk, tl, tr, tt, uk, ur, uz, vi, yi, yo, zh
​
diarize
boolean
default:"false"
Whether to diarize the audio file. Defaults to false. Setting to true will add costs proportional to diarization inference time.
​
chunk_level
ChunkLevelEnum
default:"segment"
Level of the chunks to return. Either none, segment or word. none would imply that all of the audio will be transcribed without the timestamp tokens, we suggest to switch to none if you are not satisfied with the transcription quality, since it will usually improve the quality of the results. Switching to none will also provide minor speed ups in the transcription due to less amount of generated tokens. Notice that setting to none will produce a single chunk with the whole transcription. Default value: "segment"Possible values: none, segment, word
​
batch_size
integer
default:"64"
Default value: 64Range: 1 to 64
​
prompt
string
default:""
Prompt to use for generation. Defaults to an empty string. Default value: ""
​
num_speakers
integer
Number of speakers in the audio file. Defaults to null. If not provided, the number of speakers will be automatically detected.

​
Output Schema

​
text
string
required
Transcription of the audio file
​
chunks
list<WhisperChunk>
Timestamp chunks of the audio file
​
inferred_languages
list<Enum>
required
List of languages that the audio file is inferred to be. Defaults to null.
​
diarization_segments
list<DiarizationSegment>
required
Speaker diarization segments of the audio file. Only present if diarization is enabled.

​
Input Example

{
  "audio_url": "https://storage.googleapis.com/falserverless/model_tests/whisper/dinner_conversation.mp3",
  "task": "transcribe",
  "diarize": false,
  "chunk_level": "segment",
  "batch_size": 64,
  "prompt": "",
  "num_speakers": null
}

​
Output Example

{
  "text": "María, ¿qué cenamos hoy? No sé, ¿qué cenamos? ¿Cenamos pollo frito o pollo asado o algo? Mejor a la plancha, quiero una salada. A la plancha, vale. Y hacemos una ensalada con tomate y esas cosas. Vale. Pues eso lo hacemos, ¿vale? Venga, vale.",
  "chunks": [
    {
      "text": ""
    }
  ],
  "diarization_segments": [
    {
      "speaker": ""
    }
  ]
}

​
Limitations

  • task restricted to: transcribe, translate
  • chunk_level restricted to: none, segment, word
  • batch_size range: 1 to 64