diff --git a/packages/tests/src/transcription/benchmark.spec.ts b/packages/tests/src/transcription/benchmark.spec.ts
index e93414deb79..b9f8a1ab0e4 100644
--- a/packages/tests/src/transcription/benchmark.spec.ts
+++ b/packages/tests/src/transcription/benchmark.spec.ts
@@ -9,7 +9,8 @@ import {
   transcriberFactory,
   TranscriptFile,
   TranscriptFileEvaluator,
-  TranscriptionEngine
+  TranscriptionEngine,
+  TranscriptionModel
 } from '@peertube/peertube-transcription'
 
 interface TestResult {
@@ -101,9 +102,15 @@ describe('Transcribers benchmark', function () {
       models.forEach((modelName) => {
         it(`Run ${transcriberName} transcriber benchmark with ${modelName} model`, async function () {
           this.timeout(15 * 1000 * 60) // 15 minutes
-          const model = { name: modelName }
+          const model = new TranscriptionModel(modelName)
           const uuid = short.generate()
-          const transcriptFile = await transcriber.transcribe(mediaFilePath, model, 'fr', 'txt', uuid)
+          const transcriptFile = await transcriber.transcribe({
+            mediaFilePath,
+            model,
+            language: 'fr',
+            format: 'txt',
+            runId: uuid
+          })
           const evaluator = new TranscriptFileEvaluator(referenceTranscriptFile, transcriptFile)
           await new Promise(resolve => setTimeout(resolve, 1))
 
diff --git a/packages/tests/src/transcription/transcript/transcript-evaluator.spec.ts b/packages/tests/src/transcription/transcript/transcript-evaluator.spec.ts
index a5db1e778d3..56a72033043 100644
--- a/packages/tests/src/transcription/transcript/transcript-evaluator.spec.ts
+++ b/packages/tests/src/transcription/transcript/transcript-evaluator.spec.ts
@@ -7,7 +7,7 @@ import { expect } from 'chai'
 
 describe('Transcript File Evaluator', function () {
   const transcriptDirectory = buildAbsoluteFixturePath('transcription/transcript-evaluator')
-  const referenceTranscriptFilepath = buildAbsoluteFixturePath('transcription/transcript/reference.txt')
+  const referenceTranscriptFilePath = buildAbsoluteFixturePath('transcription/transcript/reference.txt')
 
   before(async function () {
     await mkdir(transcriptDirectory, { recursive: true })
@@ -29,7 +29,7 @@ describe('Transcript File Evaluator', function () {
 
   it(`evaluation must return coherent wer & cer`, async function () {
     const reference = new TranscriptFile({
-      path: referenceTranscriptFilepath,
+      path: referenceTranscriptFilePath,
       language: 'fr',
       format: 'txt'
     })
diff --git a/packages/tests/src/transcription/whisper/transcriber/openai-transcriber.spec.ts b/packages/tests/src/transcription/whisper/transcriber/openai-transcriber.spec.ts
index e07d2297fed..475ec3744f5 100644
--- a/packages/tests/src/transcription/whisper/transcriber/openai-transcriber.spec.ts
+++ b/packages/tests/src/transcription/whisper/transcriber/openai-transcriber.spec.ts
@@ -4,7 +4,7 @@ import { createLogger } from 'winston'
 import { join } from 'path'
 import { mkdir, rm } from 'node:fs/promises'
 import { buildAbsoluteFixturePath, root } from '@peertube/peertube-node-utils'
-import { OpenaiTranscriber, TranscriptFile } from '@peertube/peertube-transcription'
+import { OpenaiTranscriber, TranscriptFile, TranscriptionModel, WhisperBuiltinModel } from '@peertube/peertube-transcription'
 
 config.truncateThreshold = 0
 
@@ -12,7 +12,6 @@ describe('Open AI Whisper transcriber', function () {
   const transcriptDirectory = join(root(), 'test-transcript')
   const shortVideoPath = buildAbsoluteFixturePath('video_short.mp4')
   const frVideoPath = buildAbsoluteFixturePath('transcription/videos/communiquer-lors-dune-classe-transplantee.mp4')
-
   const transcriber = new OpenaiTranscriber(
     {
       name: 'openai-whisper',
@@ -30,7 +29,7 @@ describe('Open AI Whisper transcriber', function () {
   })
 
   it('Should transcribe a media file and provide a valid path to a transcript file in `vtt` format by default', async function () {
-    const transcript = await transcriber.transcribe(shortVideoPath)
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.vtt'),
       language: 'en',
@@ -48,7 +47,7 @@ You
   })
 
   it('May produce a transcript file in the `srt` format', async function () {
-    const transcript = await transcriber.transcribe(shortVideoPath, { name: 'tiny' }, 'en', 'srt')
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'srt' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.srt'),
       language: 'en',
@@ -65,7 +64,7 @@ You
   })
 
   it('May produce a transcript file in the `txt` format', async function () {
-    const transcript = await transcriber.transcribe(shortVideoPath, { name: 'tiny' }, 'en', 'txt')
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'txt' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.txt'),
       language: 'en',
@@ -77,12 +76,13 @@ You
   })
 
   it('May transcribe a media file using a local PyTorch model', async function () {
-    await transcriber.transcribe(frVideoPath, { name: 'myLocalModel', path: buildAbsoluteFixturePath('transcription/models/tiny.pt') }, 'fr')
+    this.timeout(2 * 1000 * 60)
+    await transcriber.transcribe({ mediaFilePath: frVideoPath, model: TranscriptionModel.fromPath(buildAbsoluteFixturePath('transcription/models/tiny.pt')), language: 'en' })
   })
 
   it('May transcribe a media file in french', async function () {
-    this.timeout(45000)
-    const transcript = await transcriber.transcribe(frVideoPath, { name: 'tiny' }, 'fr', 'txt')
+    this.timeout(2 * 1000 * 60)
+    const transcript = await transcriber.transcribe({ mediaFilePath: frVideoPath, language: 'fr', format: 'txt' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'communiquer-lors-dune-classe-transplantee.txt'),
       language: 'fr',
@@ -105,8 +105,8 @@ Ensuite, il pourront lire et commenter ce de leurs camarades ou répondre aux co
   })
 
   it('May transcribe a media file in french with small model', async function () {
-    this.timeout(400000)
-    const transcript = await transcriber.transcribe(frVideoPath, { name: 'small' }, 'fr', 'txt')
+    this.timeout(5 * 1000 * 60)
+    const transcript = await transcriber.transcribe({ mediaFilePath: frVideoPath, language: 'fr', format: 'txt', model: new WhisperBuiltinModel('small') })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'communiquer-lors-dune-classe-transplantee.txt'),
       language: 'fr',
diff --git a/packages/tests/src/transcription/whisper/transcriber/timestamped-transcriber.spec.ts b/packages/tests/src/transcription/whisper/transcriber/timestamped-transcriber.spec.ts
index e8953e017f5..17f29f44da2 100644
--- a/packages/tests/src/transcription/whisper/transcriber/timestamped-transcriber.spec.ts
+++ b/packages/tests/src/transcription/whisper/transcriber/timestamped-transcriber.spec.ts
@@ -4,7 +4,15 @@ import { createLogger } from 'winston'
 import { join } from 'path'
 import { mkdir, rm } from 'node:fs/promises'
 import { buildAbsoluteFixturePath, root } from '@peertube/peertube-node-utils'
-import { OpenaiTranscriber, WhisperTimestampedTranscriber, TranscriptFile, TranscriptFileEvaluator } from '@peertube/peertube-transcription'
+import {
+  OpenaiTranscriber,
+  WhisperTimestampedTranscriber,
+  TranscriptFile,
+  TranscriptFileEvaluator,
+  TranscriptionModel,
+  WhisperTranscribeArgs,
+  WhisperBuiltinModel
+} from '@peertube/peertube-transcription'
 
 config.truncateThreshold = 0
 
@@ -29,15 +37,10 @@ describe('Linto timestamped Whisper transcriber', function () {
   })
 
   it('Should transcribe a media file and produce a transcript file in `vtt` with a ms precision', async function () {
-    const transcript = await transcriber.transcribe(
-      shortVideoPath,
-      { name: 'tiny' },
-      'fr'
-    )
-
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.vtt'),
-      language: 'fr',
+      language: 'en',
       format: 'vtt'
     }))).to.be.true
 
@@ -52,7 +55,7 @@ you
   })
 
   it('May produce a transcript file in the `srt` format with a ms precision', async function () {
-    const transcript = await transcriber.transcribe(shortVideoPath, { name: 'tiny' }, 'en', 'srt')
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'srt' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.srt'),
       language: 'en',
@@ -69,7 +72,7 @@ you
   })
 
   it('May produce a transcript file in `txt` format', async function () {
-    const transcript = await transcriber.transcribe(shortVideoPath, { name: 'tiny' }, 'en', 'txt')
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'txt' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.txt'),
       language: 'en',
@@ -81,12 +84,17 @@ you
   })
 
   it('May transcribe a media file using a local PyTorch model file', async function () {
-    await transcriber.transcribe(frVideoPath, { name: 'myLocalModel', path: buildAbsoluteFixturePath('transcription/models/tiny.pt') }, 'fr')
+    await transcriber.transcribe({ mediaFilePath: frVideoPath, model: TranscriptionModel.fromPath(buildAbsoluteFixturePath('transcription/models/tiny.pt')), language: 'en' })
   })
 
   it('May transcribe a media file in french', async function () {
-    this.timeout(45000)
-    const transcript = await transcriber.transcribe(frVideoPath, { name: 'tiny' }, 'fr', 'txt')
+    this.timeout(2 * 1000 * 60)
+    const transcript = await transcriber.transcribe({
+      mediaFilePath: frVideoPath,
+      language: 'fr',
+      format: 'txt',
+      model: new WhisperBuiltinModel('tiny')
+    })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'communiquer-lors-dune-classe-transplantee.txt'),
       language: 'fr',
@@ -118,13 +126,13 @@ Ensuite, il pourront lire et commenter ce de leur camarade, ou répondre au comm
 
   it('Should produce a text transcript similar to openai-whisper implementation', async function () {
     this.timeout(5 * 1000 * 60)
-    const transcribeArguments: Parameters<typeof transcriber.transcribe> = [
-      frVideoPath,
-      { name: 'tiny' },
-      'fr',
-      'txt'
-    ]
-    const transcript = await transcriber.transcribe(...transcribeArguments)
+    const transcribeArgs: WhisperTranscribeArgs = {
+      mediaFilePath: frVideoPath,
+      model: TranscriptionModel.fromPath(buildAbsoluteFixturePath('transcription/models/tiny.pt')),
+      language: 'fr',
+      format: 'txt'
+    }
+    const transcript = await transcriber.transcribe(transcribeArgs)
 
     const openaiTranscriber = new OpenaiTranscriber(
       {
@@ -137,7 +145,7 @@ Ensuite, il pourront lire et commenter ce de leur camarade, ou répondre au comm
       createLogger(),
       join(transcriptDirectory, 'openai-whisper')
     )
-    const openaiTranscript = await openaiTranscriber.transcribe(...transcribeArguments)
+    const openaiTranscript = await openaiTranscriber.transcribe(transcribeArgs)
 
     const transcriptFileEvaluator = new TranscriptFileEvaluator(openaiTranscript, transcript)
     expect(await transcriptFileEvaluator.wer()).to.be.below(25 / 100)
diff --git a/packages/tests/src/transcription/whisper/transcriber/whisper-ctranslate2.spec.ts b/packages/tests/src/transcription/whisper/transcriber/whisper-ctranslate2.spec.ts
index 31aef5d9ba0..ed19e3840d1 100644
--- a/packages/tests/src/transcription/whisper/transcriber/whisper-ctranslate2.spec.ts
+++ b/packages/tests/src/transcription/whisper/transcriber/whisper-ctranslate2.spec.ts
@@ -4,7 +4,13 @@ import { createLogger } from 'winston'
 import { join } from 'path'
 import { mkdir, readFile, rm } from 'node:fs/promises'
 import { buildAbsoluteFixturePath, root } from '@peertube/peertube-node-utils'
-import { Ctranslate2Transcriber, OpenaiTranscriber, TranscriptFile, TranscriptFileEvaluator } from '@peertube/peertube-transcription'
+import {
+  Ctranslate2Transcriber,
+  OpenaiTranscriber,
+  TranscriptFile,
+  TranscriptFileEvaluator,
+  TranscriptionModel, WhisperTranscribeArgs
+} from '@peertube/peertube-transcription'
 
 config.truncateThreshold = 0
 
@@ -29,7 +35,7 @@ describe('Whisper CTranslate2 transcriber', function () {
   })
 
   it('Should transcribe a media file and provide a valid path to a transcript file in `vtt` format by default', async function () {
-    const transcript = await transcriber.transcribe(shortVideoPath, { name: 'tiny' })
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en' })
     expect(await transcript.equals(new TranscriptFile({ path: join(transcriptDirectory, 'video_short.vtt') }))).to.be.true
     expect(await readFile(transcript.path, 'utf8')).to.equal(
       `WEBVTT
@@ -42,7 +48,7 @@ You
   })
 
   it('May produce a transcript file in the `srt` format', async function () {
-    const transcript = await transcriber.transcribe(shortVideoPath, { name: 'tiny' }, 'en', 'srt')
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'srt' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.srt'),
       format: 'srt'
@@ -58,7 +64,7 @@ You
   })
 
   it('May produce a transcript file in the `txt` format', async function () {
-    const transcript = await transcriber.transcribe(shortVideoPath, { name: 'tiny' }, 'en', 'txt')
+    const transcript = await transcriber.transcribe({ mediaFilePath: shortVideoPath, language: 'en', format: 'txt' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.txt'),
       format: 'txt'
@@ -69,12 +75,13 @@ You
   })
 
   it('May transcribe a media file using a local CTranslate2 model', async function () {
-    const transcript = await transcriber.transcribe(
-      shortVideoPath,
-      { name: 'myLocalModel', path: buildAbsoluteFixturePath('transcription/models/faster-whisper-tiny') },
-      'en',
-      'txt'
-    )
+    this.timeout(2 * 1000 * 60)
+    const transcript = await transcriber.transcribe({
+      mediaFilePath: shortVideoPath,
+      model: TranscriptionModel.fromPath(buildAbsoluteFixturePath('transcription/models/faster-whisper-tiny')),
+      language: 'en',
+      format: 'txt'
+    })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'video_short.txt'),
       format: 'txt'
@@ -85,8 +92,8 @@ You
   })
 
   it('May transcribe a media file in french', async function () {
-    this.timeout(45000)
-    const transcript = await transcriber.transcribe(frVideoPath, { name: 'tiny' }, 'fr', 'txt')
+    this.timeout(5 * 1000 * 60)
+    const transcript = await transcriber.transcribe({ mediaFilePath: frVideoPath, language: 'fr', format: 'txt' })
     expect(await transcript.equals(new TranscriptFile({
       path: join(transcriptDirectory, 'communiquer-lors-dune-classe-transplantee.txt'),
       language: 'fr',
@@ -109,13 +116,13 @@ Ensuite, il pourront lire et commenter ce de leur camarade, on répondra au comm
 
   it('Should produce a text transcript similar to openai-whisper implementation', async function () {
     this.timeout(5 * 1000 * 60)
-    const transcribeArguments: Parameters<typeof transcriber.transcribe> = [
-      frVideoPath,
-      { name: 'tiny' },
-      'fr',
-      'txt'
-    ]
-    const transcript = await transcriber.transcribe(...transcribeArguments)
+    const transcribeArgs: WhisperTranscribeArgs = {
+      mediaFilePath: frVideoPath,
+      model: TranscriptionModel.fromPath(buildAbsoluteFixturePath('transcription/models/tiny.pt')),
+      language: 'fr',
+      format: 'txt'
+    }
+    const transcript = await transcriber.transcribe(transcribeArgs)
     const openaiTranscriber = new OpenaiTranscriber(
       {
         name: 'openai-whisper',
@@ -127,7 +134,7 @@ Ensuite, il pourront lire et commenter ce de leur camarade, on répondra au comm
       createLogger(),
       join(transcriptDirectory, 'openai-whisper')
     )
-    const openaiTranscript = await openaiTranscriber.transcribe(...transcribeArguments)
+    const openaiTranscript = await openaiTranscriber.transcribe(transcribeArgs)
 
     const transcriptFileEvaluator = new TranscriptFileEvaluator(openaiTranscript, transcript)
     expect(await transcriptFileEvaluator.wer()).to.be.below(20 / 100)
diff --git a/packages/transcription/README.md b/packages/transcription/README.md
index 17553afb537..076e313f149 100644
--- a/packages/transcription/README.md
+++ b/packages/transcription/README.md
@@ -33,11 +33,10 @@ import { OpenaiTranscriber } from '@peertube/peertube-transcription'
     binary: 'whisper'
   });
 
-  const transcriptFile = await transcriber.transcribe(
-    './myVideo.mp4',
-    { name: 'tiny' },
-    'en', 'txt'
-  );
+  const transcriptFile = await transcriber.transcribe({
+    mediaFilePath: './myVideo.mp4',
+    format: 'txt'
+  });
 
   console.log(transcriptFile.path);
   console.log(await transcriptFile.read());
@@ -45,12 +44,15 @@ import { OpenaiTranscriber } from '@peertube/peertube-transcription'
 ```
 
 Using a local model file:
+
 ```typescript
-  const transcriptFile = await transcriber.transcribe(
-    './myVideo.mp4',
-    { name: 'my fine tuned large model', path: './models/large.pt' },
-    'en', 'txt'
-  );
+import { WhisperBuiltinModel } from '@peertube/peertube-transcription/dist'
+
+const transcriptFile = await transcriber.transcribe({
+  mediaFilePath: './myVideo.mp4',
+  model: WhisperBuiltinModel.fromPath('./models/large.pt'),
+  format: 'txt'
+});
 ```
 
 You may use the builtin Factory if you're happy with the default configuration:
diff --git a/packages/transcription/src/abstract-transcriber.ts b/packages/transcription/src/abstract-transcriber.ts
index cb776f4ed42..3556fd9f0a0 100644
--- a/packages/transcription/src/abstract-transcriber.ts
+++ b/packages/transcription/src/abstract-transcriber.ts
@@ -9,6 +9,14 @@ import { TranscriptionModel } from './transcription-model.js'
 import { TranscriptionRun } from './transcription-run.js'
 import { TranscriptFile, TranscriptFormat } from './transcript/index.js'
 
+export interface TranscribeArgs {
+  mediaFilePath: string
+  model: TranscriptionModel
+  language?: string
+  format?: TranscriptFormat
+  runId?: SUUID
+}
+
 export abstract class AbstractTranscriber {
   public static DEFAULT_TRANSCRIPT_DIRECTORY = join(root(), 'dist', 'transcripts')
 
@@ -55,11 +63,11 @@ export abstract class AbstractTranscriber {
     return model.format === 'PyTorch'
   }
 
-  abstract transcribe (
-    mediaFilePath: string,
-    model: TranscriptionModel,
-    language: string,
-    format: TranscriptFormat,
-    runId: SUUID
-  ): Promise<TranscriptFile>
+  abstract transcribe ({
+    mediaFilePath,
+    model,
+    language,
+    format = 'vtt',
+    runId = short.generate()
+  }: TranscribeArgs): Promise<TranscriptFile>
 }
diff --git a/packages/transcription/src/transcript/transcript-file-evaluator.ts b/packages/transcription/src/transcript/transcript-file-evaluator.ts
index ed5fba648c4..1262cddaf61 100644
--- a/packages/transcription/src/transcript/transcript-file-evaluator.ts
+++ b/packages/transcription/src/transcript/transcript-file-evaluator.ts
@@ -21,12 +21,12 @@ export class TranscriptFileEvaluator {
     this.hypothesisTranscriptFile = hypothesisTranscriptFile
   }
 
-  static buildArgs (referenceTranscriptFilepath: string, hypothesisTranscriptFilepath: string, ...args: string[]) {
+  static buildArgs (referenceTranscriptFilePath: string, hypothesisTranscriptFilePath: string, ...args: string[]) {
     return [
       '--reference',
-      referenceTranscriptFilepath,
+      referenceTranscriptFilePath,
       '--hypothesis',
-      hypothesisTranscriptFilepath,
+      hypothesisTranscriptFilePath,
       ...args
     ]
   }
diff --git a/packages/transcription/src/transcript/transcript-file.ts b/packages/transcription/src/transcript/transcript-file.ts
index a8b7a6dae6c..fc05593cc4b 100644
--- a/packages/transcription/src/transcript/transcript-file.ts
+++ b/packages/transcription/src/transcript/transcript-file.ts
@@ -39,6 +39,10 @@ export class TranscriptFile implements TranscriptFileInterface {
   }
 
   async equals (transcript: TranscriptFile, caseSensitive: boolean = true) {
+    if (this.language !== transcript.language) {
+      return false
+    }
+
     const content = await this.read()
     const transcriptContent = await transcript.read()
 
diff --git a/packages/transcription/src/transcription-model.ts b/packages/transcription/src/transcription-model.ts
index e9219d133c8..830dd5dbf22 100644
--- a/packages/transcription/src/transcription-model.ts
+++ b/packages/transcription/src/transcription-model.ts
@@ -1,10 +1,13 @@
+import assert from 'node:assert'
+import { existsSync } from 'node:fs'
+import { parse } from 'node:path'
+
 export type ModelFormat = 'PyTorch' | 'GGML' | 'ONNX' | 'CTranslate2' // CoreML, OpenVino, Scikit-Learn, TensorFlow/Keras, PySpark
 
-export abstract class TranscriptionModel {
+export class TranscriptionModel {
   name: string
   format?: ModelFormat
   path?: string
-  url?: string
 
   // #  - hparams
   // #  - Number of dimensions (int)
@@ -16,4 +19,16 @@ export abstract class TranscriptionModel {
   // #  - mel filters
   // #  - tokenizer vocab
   // #  - model variables
+
+  constructor (name: string, path?: string, format?: ModelFormat) {
+    this.name = name
+    this.path = path
+    this.format = format
+  }
+
+  static fromPath (path: string) {
+    assert(existsSync(path), `${path} doesn't exist.`)
+
+    return new TranscriptionModel(parse(path).name, path)
+  }
 }
diff --git a/packages/transcription/src/whisper/index.ts b/packages/transcription/src/whisper/index.ts
index ba4581d7f75..ee9cae725fa 100644
--- a/packages/transcription/src/whisper/index.ts
+++ b/packages/transcription/src/whisper/index.ts
@@ -1,2 +1,3 @@
 export * from './transcriber/index.js'
 export * from './engines.js'
+export * from './whisper-builtin-model.js'
diff --git a/packages/transcription/src/whisper/transcriber/ctranslate2-transcriber.ts b/packages/transcription/src/whisper/transcriber/ctranslate2-transcriber.ts
index 5e64718763c..b90c2bba785 100644
--- a/packages/transcription/src/whisper/transcriber/ctranslate2-transcriber.ts
+++ b/packages/transcription/src/whisper/transcriber/ctranslate2-transcriber.ts
@@ -1,20 +1,20 @@
 import { $ } from 'execa'
-import short, { SUUID } from 'short-uuid'
+import short from 'short-uuid'
 import { join } from 'path'
 import { lstat } from 'node:fs/promises'
-import { OpenaiTranscriber } from './openai-transcriber.js'
-import { TranscriptionModel } from '../../transcription-model.js'
-import { TranscriptFile, TranscriptFormat } from '../../transcript/index.js'
+import { OpenaiTranscriber, WhisperTranscribeArgs } from './openai-transcriber.js'
+import { TranscriptFile } from '../../transcript/index.js'
 import { getFileInfo } from '../../file-utils.js'
+import { WhisperBuiltinModel } from '../whisper-builtin-model.js'
 
 export class Ctranslate2Transcriber extends OpenaiTranscriber {
-  async transcribe (
-    mediaFilePath: string,
-    model: TranscriptionModel = { name: 'tiny' },
-    language: string = 'en',
-    format: TranscriptFormat = 'vtt',
-    runId: SUUID = short.generate()
-  ): Promise<TranscriptFile> {
+  async transcribe ({
+    mediaFilePath,
+    model = new WhisperBuiltinModel('tiny'),
+    language,
+    format = 'vtt',
+    runId = short.generate()
+  }: WhisperTranscribeArgs): Promise<TranscriptFile> {
     // Shall we run the command with `{ shell: true }` to get the same error as in sh ?
     // ex: ENOENT => Command not found
     const $$ = $({ verbose: true })
@@ -23,19 +23,20 @@ export class Ctranslate2Transcriber extends OpenaiTranscriber {
     if (model.path) {
       await lstat(model.path).then(stats => stats.isDirectory())
     }
-    const modelArgs = model.path ? [ '--model_directory', model.path ] : [ '--model', model.name ]
+
+    const modelArg = model.path ? [ '--model_directory', model.path ] : [ '--model', model.name ]
+    const languageArg = language ? [ '--language', language ] : []
 
     this.createRun(runId)
     this.startRun()
     await $$`${this.engine.binary} ${[
       mediaFilePath,
-      ...modelArgs,
+      ...modelArg,
       '--output_format',
       format,
       '--output_dir',
       this.transcriptDirectory,
-      '--language',
-      language
+      ...languageArg
     ]}`
     this.stopRun()
 
diff --git a/packages/transcription/src/whisper/transcriber/index.ts b/packages/transcription/src/whisper/transcriber/index.ts
index b1d11724259..950c39b0731 100644
--- a/packages/transcription/src/whisper/transcriber/index.ts
+++ b/packages/transcription/src/whisper/transcriber/index.ts
@@ -1,5 +1,3 @@
 export * from './ctranslate2-transcriber.js'
-export * from './transformers-js-transcriber.js'
-export * from './transformers-transcriber.js'
 export * from './openai-transcriber.js'
 export * from './timestamped-transcriber.js'
diff --git a/packages/transcription/src/whisper/transcriber/openai-transcriber.ts b/packages/transcription/src/whisper/transcriber/openai-transcriber.ts
index d9f8ce13b71..b6be87227da 100644
--- a/packages/transcription/src/whisper/transcriber/openai-transcriber.ts
+++ b/packages/transcription/src/whisper/transcriber/openai-transcriber.ts
@@ -1,23 +1,27 @@
 import { join } from 'path'
 import { $ } from 'execa'
-import short, { SUUID } from 'short-uuid'
-import { TranscriptionModel } from '../../transcription-model.js'
-import { TranscriptFile, TranscriptFormat } from '../../transcript/index.js'
-import { AbstractTranscriber } from '../../abstract-transcriber.js'
+import short from 'short-uuid'
+import { TranscriptFile } from '../../transcript/index.js'
+import { AbstractTranscriber, TranscribeArgs } from '../../abstract-transcriber.js'
 import { getFileInfo } from '../../file-utils.js'
+import { WhisperBuiltinModel } from '../whisper-builtin-model.js'
+import { TranscriptionModel } from '../../transcription-model.js'
+
+export type WhisperTranscribeArgs = Omit<TranscribeArgs, 'model'> & { model?: TranscriptionModel }
 
 export class OpenaiTranscriber extends AbstractTranscriber {
-  async transcribe (
-    mediaFilePath: string,
-    model: TranscriptionModel = { name: 'tiny' },
-    language: string = 'en',
-    format: TranscriptFormat = 'vtt',
-    runId: SUUID = short.generate()
-  ): Promise<TranscriptFile> {
+  async transcribe ({
+    mediaFilePath,
+    model = new WhisperBuiltinModel('tiny'),
+    language,
+    format = 'vtt',
+    runId = short.generate()
+  }: WhisperTranscribeArgs): Promise<TranscriptFile> {
     // Shall we run the command with `{ shell: true }` to get the same error as in sh ?
     // ex: ENOENT => Command not found
     const $$ = $({ verbose: true })
     const { baseName } = getFileInfo(mediaFilePath)
+    const languageArg = language ? [ '--language', language ] : []
 
     this.createRun(runId)
     this.startRun()
@@ -29,8 +33,7 @@ export class OpenaiTranscriber extends AbstractTranscriber {
       format,
       '--output_dir',
       this.transcriptDirectory,
-      '--language',
-      language
+      ...languageArg
     ]}`
     this.stopRun()
 
diff --git a/packages/transcription/src/whisper/transcriber/timestamped-transcriber.ts b/packages/transcription/src/whisper/transcriber/timestamped-transcriber.ts
index e23e3d3eeb1..de2f760127a 100644
--- a/packages/transcription/src/whisper/transcriber/timestamped-transcriber.ts
+++ b/packages/transcription/src/whisper/transcriber/timestamped-transcriber.ts
@@ -1,24 +1,25 @@
 import { $ } from 'execa'
-import short, { SUUID } from 'short-uuid'
+import short from 'short-uuid'
 import assert from 'node:assert'
 import { join } from 'node:path'
 import { existsSync } from 'node:fs'
 import { rename } from 'node:fs/promises'
-import { TranscriptionModel } from '../../transcription-model.js'
-import { TranscriptFile, TranscriptFormat } from '../../transcript/index.js'
+import { TranscriptFile } from '../../transcript/index.js'
 import { getFileInfo } from '../../file-utils.js'
-import { OpenaiTranscriber } from './openai-transcriber.js'
+import { OpenaiTranscriber, WhisperTranscribeArgs } from './openai-transcriber.js'
+import { WhisperBuiltinModel } from '../whisper-builtin-model.js'
 
 export class WhisperTimestampedTranscriber extends OpenaiTranscriber {
-  async transcribe (
-    mediaFilePath: string,
-    model: TranscriptionModel,
-    language: string,
-    format: TranscriptFormat = 'vtt',
-    runId: SUUID = short.generate()
-  ): Promise<TranscriptFile> {
+  async transcribe ({
+    mediaFilePath,
+    model = new WhisperBuiltinModel('tiny'),
+    language,
+    format = 'vtt',
+    runId = short.generate()
+  }: WhisperTranscribeArgs): Promise<TranscriptFile> {
     const $$ = $({ verbose: true })
     const { baseName, name } = getFileInfo(mediaFilePath)
+    const languageArg = language ? [ '--language', language ] : []
 
     this.createRun(runId)
     this.startRun()
@@ -29,7 +30,8 @@ export class WhisperTimestampedTranscriber extends OpenaiTranscriber {
       '--output_format',
       'all',
       '--output_dir',
-      this.transcriptDirectory
+      this.transcriptDirectory,
+      ...languageArg
     ]}`
     this.stopRun()
 
diff --git a/packages/transcription/src/whisper/transcriber/transformers-js-transcriber.ts b/packages/transcription/src/whisper/transcriber/transformers-js-transcriber.ts
deleted file mode 100644
index d06e971a52a..00000000000
--- a/packages/transcription/src/whisper/transcriber/transformers-js-transcriber.ts
+++ /dev/null
@@ -1,21 +0,0 @@
-import { TranscriptionModel } from '../../transcription-model.js'
-import { AbstractTranscriber } from '../../abstract-transcriber.js'
-import { TranscriptFile, TranscriptFormat } from '../../transcript/index.js'
-
-// Disable local models
-// env.allowLocalModels = true
-
-export class TransformersJsTranscriber extends AbstractTranscriber {
-  async transcribe (
-    mediaFilePath: string,
-    model: TranscriptionModel,
-    language: string,
-    format: TranscriptFormat = 'vtt'
-  ): Promise<TranscriptFile> {
-    return Promise.resolve(undefined)
-    // return pipeline('automatic-speech-recognition', 'no_attentions', {
-    //   // For medium models, we need to load the `no_attentions` revision to avoid running out of memory
-    //   revision: [].includes('/whisper-medium') ? 'no_attentions' : 'main'
-    // })
-  }
-}
diff --git a/packages/transcription/src/whisper/transcriber/transformers-transcriber.ts b/packages/transcription/src/whisper/transcriber/transformers-transcriber.ts
deleted file mode 100644
index 71a53f92318..00000000000
--- a/packages/transcription/src/whisper/transcriber/transformers-transcriber.ts
+++ /dev/null
@@ -1,43 +0,0 @@
-import { TranscriptionModel } from '../../transcription-model.js'
-import { TranscriptFile, TranscriptFormat } from '../../transcript/index.js'
-import { AbstractTranscriber } from '../../abstract-transcriber.js'
-import { $ } from 'execa'
-import { join } from 'path'
-
-export class TransformersTranscriber extends AbstractTranscriber {
-  async transcribe (
-    mediaFilePath: string,
-    model: TranscriptionModel,
-    language: string,
-    format: TranscriptFormat = 'vtt'
-  ): Promise<TranscriptFile> {
-    const $$ = $({ verbose: true })
-    // const ffmpegChildProcess = $$`ffmpeg ${[
-    //   '-i',
-    //   mediaFilePath,
-    //   '-vn', // no video
-    //   '-ar',
-    //   16000, // set the audio sampling frequency
-    //   '-ac',
-    //   '1', // set the number of audio channels to 1 since Vosk is expecting mono
-    //   '-bufsize',
-    //   1000, // set a buffer size to provide a steady flow of frames
-    //   '-'
-    // ]}`
-
-    await $$`transformers-cli ${[
-      '--task',
-      'automatic-speech-recognition',
-      '--model',
-      'openai/whisper-tiny',
-      '--input',
-      mediaFilePath
-    ]}`
-
-    return new TranscriptFile({
-      language,
-      path: join(this.transcriptDirectory, `test.${format}`),
-      format
-    })
-  }
-}
diff --git a/packages/transcription/src/whisper/whisper-builtin-model.ts b/packages/transcription/src/whisper/whisper-builtin-model.ts
new file mode 100644
index 00000000000..32981ad2030
--- /dev/null
+++ b/packages/transcription/src/whisper/whisper-builtin-model.ts
@@ -0,0 +1,11 @@
+import { TranscriptionModel } from '../transcription-model.js'
+
+export type WhisperBuiltinModelName = 'tiny' | 'base' | 'small' | 'medium' | 'large' | 'large-v2' | 'large-v3'
+
+export class WhisperBuiltinModel extends TranscriptionModel {
+
+  // eslint-disable-next-line @typescript-eslint/no-useless-constructor
+  constructor (name: WhisperBuiltinModelName) {
+    super(name)
+  }
+}