Text to speech
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
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 music
- Free limit: Free to use. Require to login account.
- Free limit: Free to use. Require to login google account.
- Model: MusicLM
Speech to text 工具
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
openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision
- Language: 99 languages
- Sample code:
- Related:
- Free limit:
🎙️ MacWhisper https://goodsnooze.gumroad.com/l/macwhisper
- Language: 100 languages
- Sample code:
- Related:
- Free limit:
- 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:
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
- 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.