SpeechGen: Convert Text to Audio with Over 5,000 Voices
Sign up

SpeechGen

Tags
Text-To-Speech
Pricing model
Free Trial
Upvote 0

SpeechGen assists creators in converting scripts and subtitles into audio for videos, lessons, and presentations. The browser-based editor includes over 5,000 voices spanning 150 languages, with voice samples provided to aid in selecting a speaker. You can allocate different voices to specific sections of the script, adjust the delivery and pauses using SSML, and incorporate background music.

The service also offers tools for converting subtitles to audio and provides a REST API for integrating speech generation with other workflows. The generated audio can be downloaded in MP3, WAV, or FLAC formats.

Pricing starts at $4.99 with one-time, pay-as-you-go credit packs. A free trial is available. The amount of credits used depends on the length of the text and the chosen voice quality.

Go to SpeechGen

Similar neural networks:

Freemium
Upvote 0
Text-To-Speech
0
11.ai
11.ai is a leading AI-driven voice synthesis platform that produces highly realistic digital voices using voice cloning and text-to-speech features. It generates authentic speech with genuine emotional expression in various languages, offering value to content creators, game developers, marketers, and businesses that want professional-grade voiceovers without the expenses or limitations of conventional recording. Users prefer 11.ai for its outstanding audio quality, speed, and the capability to easily incorporate tailored voices into different applications via its API, enhancing the appeal and accessibility of audio experiences.
Paid
Upvote 0
Text-To-Speech Text-To-Video
0
Synthesys Studio
Synthesys stands out as a top AI-driven virtual media platform, allowing users to effortlessly create professional AI voiceovers and videos. It provides a vast selection of professional voices, including 74 Humatars, with 38 female and 36 male options, across 66 languages and 254 styles. The platform also offers cloud-based applications, complete customization, and high-resolution output. Synthesys is ideal for producing explainer videos, eLearning content, social media material, product descriptions, and more.
Freemium
Upvote 0
Text-To-Speech
0
Eleven Labs
Eleven Labs' platform utilizes AI to produce long-form speech with natural and engaging voices for creators and publishers.