When using the API from within your software/application, you simply send text to the ReadSpeaker speechCloud API servers and receive audio data in the file format you specify as a response. This file can be stored on your server for reuse or further distribution or other use.
We provide several API parameters that your application can use to give you full control over the produced audio. With these parameters, you can customize the language, voice, reading speed, pitch, audio format, bitrate, etc. according to your preferences.
ReadSpeaker speechCloud API can also easily be used in the very popular open source communication application platform Asterisk to add text-to-speech capabilities to PBX/IVR systems.
Fully automated text to speech conversion
Built-in customer-specific dictionary where you can control how certain words are read
Multiple audio file formats (A-law, u-law, PCM, WAV, Ogg, MP3)
Choice of several languages and voices using state-of-the art speech synthesis
Sample code in different programming languages, such as PHP, Java, Objective C, and C++
AGI script which supports most versions on Asterisk on Linux
Have more control over how the text is read with SSML input support. When activated in your account, it is possible to insert pauses/breaks of certain length, insert phonetic transcriptions and do voice and language switching in the same text.
Statistics interface (via web and/or API)
High-security hosting environment with a high level of redundancy and failover
Access to timing information makes it possible to build a highlighting solution within the API.