Text to speech: Difference between revisions
| Line 81: | Line 81: | ||
* Related: | * Related: | ||
* Free limit: | * Free limit: | ||
* Related: | |||
** [https://huggingface.co/spaces/Xenova/whisper-webgpu Whisper WebGPU - a Hugging Face Space by Xenova] | |||
** [https://github.com/aaaddress1/Whisper.py?fbclid=IwAR1rwZH-USj2NIt8pLYRGhIqWvQWUj1FQTx83qpBncno3ANWDUBI_duWr9M 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:[https://www.playpcesor.com/2023/04/whisperdesktop-ai.html 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 {{Mac}} | |||
[https://cloud.google.com/speech/?hl=zh-tw 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 [https://cloud.google.com/speech-to-text/pricing 定價 | Cloud Speech API Documentation | Google Cloud]。 {{access | date = 2018-09-04}} | [https://cloud.google.com/speech/?hl=zh-tw 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 [https://cloud.google.com/speech-to-text/pricing 定價 | Cloud Speech API Documentation | Google Cloud]。 {{access | date = 2018-09-04}} | ||
| Line 127: | Line 131: | ||
* Related: | * Related: | ||
* Free limit: 5 minutes | * Free limit: 5 minutes | ||
[https://github.com/SYSTRAN/faster-whisper?tab=readme-ov-file SYSTRAN/faster-whisper: Faster Whisper transcription with CTranslate2] | [https://github.com/SYSTRAN/faster-whisper?tab=readme-ov-file SYSTRAN/faster-whisper: Faster Whisper transcription with CTranslate2] | ||
| Line 148: | Line 146: | ||
[https://www.larksuite.com/ Lark | Business Chat & Collaboration Tool] ([https://zh.wikipedia.org/wiki/%E9%A3%9E%E4%B9%A6 飞书 - 維基百科,自由的百科全書]) | [https://www.larksuite.com/ Lark | Business Chat & Collaboration Tool] ([https://zh.wikipedia.org/wiki/%E9%A3%9E%E4%B9%A6 飞书 - 維基百科,自由的百科全書]) | ||
* Language: | * Language: | ||
* Sample code: | * Sample code: | ||
Revision as of 16:13, 16 February 2025
Text to speech services
Text to speech 工具
Pocket on Android
or iOS Listening to Articles in Pocket with Text-to-Speech - Pocket Support
- Object: Saved web page
the content may not be saved completed but truncated.
- Object: Input text
- Speed of speech:
Allow to slow down the speed of speech (ttsspeed=0.24)
Google 文字轉語音 - Google Play Android 應用程式 on Android
- Object: Some books on Google play
博客來電子書櫃 on Android
使用 Google 文字轉語音的服務
- Object: books
Kindle 部分版本支援 Amazon.com Help: Features Available in Kindle Books
- 物件: 書籍
文字MP3 on Win
/ TTS文字轉語音引擎
- 物件: 輸入文字 或 Excel
- 授權:如果需要購買「公播商業授權」等其它語音相關應用需求需要與廠商聯絡!

- 物件: 「OneNote、Outlook、PowerPoint 及 Word」
- 免費方案:200 V-points
Bing Speech API - 語音辨識 | Microsoft Azure
- Object: Input text
Cloud Text-to-Speech - Speech Synthesis | Google Cloud
- Object: Input text
Wizzard Speech I ATT Natural Voices SDK [Last visited: 2018-09-04]
- Object: Input text
- Language: English, Spanish
vozMe - From text to speech (speech synthesis) [Last visited: 2018-09-04]
- Object: Input text
- Language: English, Español, Italiano, Hindi, Português, Català
Read Aloud: 文字語音朗讀助理 - Chrome 線上應用程式商店
- 物件: 網頁
- 語言: 中
How 哥產生器!開發者整理素材,讓 HowHow 幫你講任何中文句子 - INSIDE
- 物件: 文字
- 語言: 中
ElevenLabs - Generative AI Text to Speech & Voice Cloning
- 物件: 文字
- 語言: 輸入中文,會聽到老外腔講中文
$ Voicenotes | AI Voice Notes App
- Input: Simply record your voice directly in the app. (
Note: File uploads are not currently supported) - Language: Automatic language detection. For example, if you record in spoken Chinese, you'll receive a Chinese transcript.
Introducing Stable Audio 2.0 — Stability AI
- 尚未提供線上服務
停止服務 工研院文字轉語音Web服務
- 物件: 網頁
- 語言: 中、英文、台語
Text to sound effect
OptimizerAI : Get Unlimited Sounds
- Free Usage limit: Free for use, downloading the file is not permitted.
Speech to text 工具
openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision
- Language: 99 languages
- Sample code:
- Related:
- Free limit:
- Related:
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]
- Object: microphone & audio file (For audio file which longer than 1 minute, upload files to Google cloud storage.
- Language: 120 languages [1]
- Sample code:
- Related: Troubleshooting of Google cloud speech to text)
Bing 語音 API - 語音辨識軟體 | Microsoft Azure
- Object: Audio file. Format: wav & ogg[2]
- Language: Traditional Chinese, Simplified Chinese & English and more on the list[3]
- Sample code: Azure-Samples/SpeechToText-REST: REST Samples of Speech To Text API
- Related:
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]
- Object: Audio file. Format: wav & speex [4]
- Language: Traditional Chinese & Simplified Chinese [5]
- 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
- Object: Video
- Language:
- Sample code:
- Related:
语音识别 - 讯飞开放平台 [Last visited: 2018-09-06]
- Object: speex audio file less than 1 minute [6]
- 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]
- Object: Audio file (Stored in S3 bucket). "Valid formats for the audio are mp3, mp4, wav and flac. [7]"
- 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)
- Language:
- Sample code:
- Related:
- 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:
Further reading
如果改善 TTS
Related keywords
References
- ↑ Language Support | Cloud Speech-to-Text API | Google Cloud
- ↑ 語音轉換文字 API 參考(REST)-語音服務 - Azure Cognitive Services | Microsoft Docs
- ↑ 語言支援-語音服務 - Azure Cognitive Services | Microsoft Docs
- ↑ 文件中心 - OLAMI - 歐拉蜜人工智慧開放平台
- ↑ olami-api-quickstart-curl-samples/cloud-speech-recognition at master · olami-developers/olami-api-quickstart-curl-samples
- ↑ 语音听写 · 科大讯飞REST_API开发指南
- ↑ StartTranscriptionJob - Amazon Transcribe For best results, use a lossless format, such as FLAC or WAV with PCM 16-bit encoding.Your audio input can be sampled at any rate between 8000 and 48000 Hz. We suggest that you use 8000 Hz for low-quality audio and 16000 Hz for high-quality audio.