Speech to text

Speech to text 工具

openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision

• Support Language: 99 languages
• Input file: Audio files
• Speaker identification: Need to integrate with (1) m-bain/whisperX: WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization) or (2) pyannote/pyannote-audio: Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
• Real-Time Subtitles or Translation: Not Available
• Related:
  • Whisper WebGPU - a Hugging Face Space by Xenova
  • aaaddress1/Whisper.py: 白癡喔還要下 pip install 誰會用啦—隨開即用 Windows 版 OpenAI Whisper 逐字稿產生器 on Win 介紹：WhisperDesktop 語音轉文字免費單機軟體，AI 影片字幕實測比較
  • 🎙️ MacWhisper https://goodsnooze.gumroad.com/l/macwhisper on macOS

Speech API - 語音辨識  |  Google Cloud 「語音轉文字採用機器學習技術」，免費版語音辨識的額度 60 分鐘，詳 定價  |  Cloud Speech API Documentation  |  Google Cloud。 [Last visited: 2018-09-04]

• Input: microphone & audio file (For audio file which longer than 1 minute, upload files to Google cloud storage.
• Language: 120 languages
• Sample code:
• Related: Troubleshooting of Google cloud speech to text)

Bing 語音 API - 語音辨識軟體 | Microsoft Azure

• Input: Audio file. Format: wav & ogg
• Language: Traditional Chinese, Simplified Chinese & English and more on the list
• Sample code: Azure-Samples/SpeechToText-REST: REST Samples of Speech To Text API
• Related:

Clipchamp [Last visited: 2025-04-02]

• Input: audio or video file
• Support Language: 80+ languages
• Comments: The free version seems to have no limitation on video duration, and you can also use AI to convert videos or audio into transcripts for free. However, during testing, the subtitles displayed for each time code were not complete sentences.

Meeting Ink - AI notetaker to transcribe and summarize your meetings and recordings.

• Support Language:
• Input file: Audio files
• Speaker identification: Available
• Real-Time Subtitles or Translation: Pro plan only $
• Free limit: 30 minutes max

OLAMI 中文語音辨識 API｜歐拉蜜人工智慧開放平台（威盛電子） [Last visited: 2018-09-05]

• Input: Audio file. Format: wav & speex
• Language: Traditional Chinese & Simplified Chinese
• Sample code: olami-developers/olami-api-quickstart-curl-samples
• Related: Troubleshooting of Olami speech to text

影片要產生文字，可利用 youtube 的 Use automatic captioning - YouTube Help，約需要半天時間 [Last visited: 2018-09-04] 教學: YouTube超佛心，自動幫你加入字幕！ | T客邦

• Input: Video
• Language:
• Sample code:
• Related:

语音识别 - 讯飞开放平台 [Last visited: 2018-09-06]

• Input: speex audio file less than 1 minute
• Language: 中文（普通话）、英文、中文（粤语）、中文（四川话）
• Sample code:
• Related:

Amazon Transcribe – 自動語音辨識 – AWS (API documentation: What Is Amazon Transcribe? - Amazon Transcribe) [Last visited: 2018-09-05]

• Input: Audio file (Stored in S3 bucket). "Valid formats for the audio are mp3, mp4, wav and flac. "
• Language: English, Spanish
• Sample code:
• Related:

Web Speech to Text 教學: 免費！中文影片語音轉文字字幕，支援超大影片與長時間錄音

• 物件: 電腦影像、聲音、YouTube 網址
• 語言: 中文、英文、日文、韓文

Voicetapp - AI Voice to Text Transcription

• Language: 中文、英文等多種語言
• Sample code:
• Related:
• Free limit: 5 minutes

SYSTRAN/faster-whisper: Faster Whisper transcription with CTranslate2

• Language: Fork from OpenAI Whisper
• Sample code: [1]
• Related:
• Free limit:
• Instruction: 雄::gsyan: 以 Faster Whisper 將影音辨識為文字檔案(字幕或逐字稿)

Good Tape

• Support Language:
• Input file: Audio files
• Speaker identification: Available
• Real-Time Subtitles or Translation: Not Available
• Free limit: 20 minutes max

Lark | Business Chat & Collaboration Tool (飞书 - 維基百科，自由的百科全書)

• Language:
• Sample code:
• Related:
• Free limit:

Const-me/Whisper: High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model on Win

• Language:
• Sample code:
• Related:
• Free limit:

iTranscribe: Transcribe Audio & Video to Text

• Language:
• Sample code:
• Related:
• Free limit:

剪映官網-全能易用的桌面端剪輯軟體-輕而易剪 上演大幕 中國軟體

• Language:
• Sample code:
• Related:
• Free limit: