Cloud Infinite
- Release Notes and Announcements
- Product Introduction
- Purchase Guide
- Billing Mode
- Billable Items
- Features
- Image Processing
- Media Processing
- Content Moderation
- AI Content Recognition
- File Processing
- Getting Started
- Console Guide
- Bucket Management
- Bucket Tagging
- Image Processing
- Image Compression Service
- Content Moderation
- Job and Workflow
- Workflow
- Data Monitoring
- Practical Tutorial
- Image Processing Practices
- Workflow Practices
- Developer Manual
- Access Management
- API Documentation
- Bucket Configuration
- Image Processing
- Image Styles
- Basic Image Processing
- Image Advanced Compression
- Queue APIs
- AI-Based Content Recognition
- Face Recognition
- FaceID
- Image OCR
- Speech Recognition
- Job APIs
- Search by Image
- Queue APIs
- Service Configuration
- Smart Audio
- Speech Bucket APIs
- Media Processing
- Media Processing Service Configuration APIs
- Media Bucket APIs
- Sync Media Processing Service
- Getting Media Screenshot
- Getting Media Information
- Private M3U8
- Content Moderation
- Image Moderation
- Video Moderation
- Audio Moderation
- Text Moderation
- File Moderation
- File Preview
- File Transcoding
- Async Processing Job APIs
- Async Processing Queue APIs
- File Processing
- Hash Calculation
- File Decompression
- Multi-File Zipping
- Job and Workflow
- Workflow APIs
- Workflow Instance
- Job APIs
- Media Processing
- Submitting Media Processing Job
- Canceling Media Processing Job
- Querying Media Processing Job
- Media Processing Job Callback
- Image Processing
- Submit Image Processing Job
- Canceling Image Processing Job
- Querying Image Processing Job
- Multi-Job Processing
- Submitting Multiple Jobs
- AI-Based Content Recognition
- Submitting Content Recognition Job
- Querying Content Recognition Job
- Content Recognition Job Callback
- Template APIs
- Media Processing
- Creating Media Processing Template
- Deleting Media Processing Template
- Querying Media Processing Template
- Updating Template
- AI-Based Content Recognition
- Creating AI-Based Content Recognition Template
- Querying AI-Based Content Recognition Template
- Updating AI-Based Content Recognition Template
- Appendix
- SDK Documentation
- Android SDK
- Basic Image Processing
- iOS SDK
- Basic Image Processing
- COS Android SDK
- C SDK
- Media Processing
- Content Moderation
- Content Recognition
- C++ SDK
- Image Processing
- Media Processing
- .NET(C#) SDK
- Image Processing
- Media Processing
- Go SDK
- Image Processing
- Media Processing
- File Preview
- Content Moderation
- AI-Based Content Recognition
- File Processing
- COS iOS SDK
- Java SDK
- Image Processing
- AI-Based Content Recognition
- Media Processing
- File Preview
- File Processing
- JavaScript SDK
- Image Processing
- Media Processing
- File Processing
- Node.js SDK
- Image Processing
- Media Processing
- PHP SDK
- Image Processing
- Media Processing
- File Processing
- Content Recognition
- Job APIs
- Template APIs
- File Processing
- Python SDK
- Media Processing
- Content Moderation
- Content Recognition
- Speech Recognition
- File Processing
- Template APIs
- File Processing
- File Decompression
- Mini Program SDK
- Image Processing
- Media Processing
- Content Moderation
- Personal Information Protection Policy for SDK
- FAQs
- Media Processing
- Related Agreements
Text To Speech
Last updated: 2024-01-31 16:33:35
Overview
The text to speech feature converts text to natural-sounding and smooth speeches in a variety of voices in PCM, WAV, or MP3 format through advanced deep learning technology. It comes with various features such as speech speed, voice, and volume adjustment. It is suitable for diverse scenarios, including smart customer service, voice interaction, audiobook, and accessible broadcasting.
Use Cases
Smart customer service
The text to speech feature works with speech recognition and natural language processing modules to close the loop of human-machine interaction in customer service bot and task service robot use cases. The highly natural bot voices make human-machine interaction more natural.
Audiobook
Electronic courseware, novels, and other types of text can be converted to audios of different voices to create audiobooks that can be listened to at any time.
Directions
You can use the text to speech feature through jobs or workflows. In order to improve the operational efficiency and reduce repetitive operations, CI offers the template feature, which is a configuration item in jobs and workflows. You can save common parameter combinations as templates and reuse them directly in subsequent operations, with no need to set the parameters every time you start a job. You can customize text-to-speech templates as follows:
Custom templates: You can create a template in the console as instructed in Template. You can also create, modify, find, and delete a template through API as instructed in Creating Text-to-Speech Template, Updating Text-to-Speech Template, DescribeMediaTemplates, and DeleteMediaTemplate respectively.
Voice description
Name | Voice Parameter Value | Type | Use Case | Supported Languages | Voice Quality |
Ruxue | ruxue | Standard female voice | General | Chinese, Chinese-English mix | Standard |
Aixiaonan | aixiaonan | Sweet female voice | General, social | Chinese, Chinese-English mix | Premium |
Aixiaoxing | aixiaoxing | Commentary male voice | General, commentary | Chinese, Chinese-English mix | Premium |
Alice | alice | Standard female voice | General | English | Premium |
Multi-sentiment voice description
Name | Voice Parameter Value | Sentiment Category |
Aixiaoxing | aixiaoxing | Neutral, broadcasting, calm, excited |
Note:
Text to speech supports async and sync modes. If the input text is short, such as in the one-sentence scenario, the sync mode is recommended.
Through job
You can create a text-to-speech job through the console or API for existing data stored in COS.
Console: You can create a text-to-speech job visually in the CI console as instructed in Job.
API: You can create a text-to-speech job through API as instructed in Submitting Text-to-Speech Job.
Through workflow
CI provides the workflow service. You can enable a workflow for a bucket or a specific path. Then, text to speech will be automatically performed on files uploaded to the bucket or path, and the generated audio files will be saved in the specified location.
Creating workflow
Creating, deleting, querying, and updating workflow through API
You can create, delete, query, and update a workflow through API as instructed in Creating Workflow, Deleting Workflow, Querying Workflow, and Updating Workflow respectively.
Was this page helpful?
You can also Contact Sales or Submit a Ticket for help.
Yes
No