Whisper | Speech to Text

fal-ai/whisper

Whisper is a model for speech transcription and translation.

Inference

Commercial use

Schema

LLMs

Playground API

About

Generate

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/whisper", {
  input: {
    audio_url: "https://storage.googleapis.com/falserverless/model_tests/whisper/dinner_conversation.mp3"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.

import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("fal-ai/whisper", {
  input: {
    audio_url: "https://storage.googleapis.com/falserverless/model_tests/whisper/dinner_conversation.mp3"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("fal-ai/whisper", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("fal-ai/whisper", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

audio_url string* required

URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm.

task TaskEnum

Task to perform on the audio file. Either transcribe or translate. Default value: "transcribe"

Possible enum values: transcribe, translate

language LanguageEnum

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 enum 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

Whether to diarize the audio file. Defaults to false. Setting to true will add costs proportional to diarization inference time.

chunk_level ChunkLevelEnum

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 enum values: none, segment, word

version VersionEnum

Version of the model to use. All of the models are the Whisper large variant. Default value: "3"

Possible enum values: 3

batch_size integer

Default value: 64

prompt string

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.

{
  "audio_url": "https://storage.googleapis.com/falserverless/model_tests/whisper/dinner_conversation.mp3",
  "task": "transcribe",
  "chunk_level": "segment",
  "version": "3",
  "batch_size": 64,
  "num_speakers": null
}

Output#

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.

{
  "text": "",
  "chunks": [
    {
      "text": ""
    }
  ],
  "diarization_segments": [
    {
      "speaker": ""
    }
  ]
}

Other types#

WhisperChunk#

timestamp list<void>* required

Start and end timestamp of the chunk

text string* required

Transcription of the chunk

speaker string

Speaker ID of the chunk. Only present if diarization is enabled.

DiarizationSegment#

timestamp list<void>* required

Start and end timestamp of the segment

speaker string* required

Speaker ID of the segment

Whisper Speech to Text

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

WhisperChunk#

DiarizationSegment#