tencent cloud

Tencent Cloud Text To Speech (TTS) turns text into natural-sounding speech in multiple voices and different languages. It supports the Speech Synthesis Markup Language (SSML) and allows you to adjust the volume and speech rate so you can customize speech for many use cases. TTS can be widely used in smart customer service, audiobook production, and news broadcasting to provide a closed loop human-machine interaction experience and increase the development efficiency of your voice applications.

Features

Various voice types

TTS currently supports 53 types of male and female voices, well meeting the needs of diverse use cases such as audiobook, customer service, navigation, and notification.

Supported languages

TTS supports speech synthesis in Chinese, English and Chinese-English mix.

Parameter configuration

TTS allows you to configure the volume, speech rate (0.6X to 1.5X), and sample rate (8 kHz or 16 kHz for apps and phone lines).

Strengths

Highly lifelike speech

TTS is built on industry-leading technologies that can quickly create highly natural-sounding, realistic speech for many different scenarios. It enables your devices and applications to talk to users and deliver more lifelike interaction.

Flexible settings

• TTS supports speech synthesis in Chinese, English, and Chinese-English mix.
• It allows you to select volume, speech rate, and other attributes for your specific business needs.
• It can generate speeches in basic audio files and live audio streams.
• It supports phone call, app, and other scenarios for your choice.

Diverse voices

TTS offers many male and female voice options for diverse use cases, such as customer service, audiobook, and message broadcasting.

Use Cases

Bot speech

TTS 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 production

Electronic courseware, novels, and other types of text can be imported to the offline TTS engine to create audiobooks that can be listened to at any time.

Voice broadcasting

In voice navigation and news apps, TTS can quickly generate high-quality broadcast speeches, making it easier for users on the go to get information through audio.