Text-to-Speech Providers
These are the voices you can use on AudioStack
AudioStack offers one of the largest and most diverse collections of synthetic voice providers on the market today. This gives you the perfect starting point to build great audio.
Through AudioStack, you can use the world's best TTS voices within a single infrastructure.
AudioStack will take care of API maintenance and keeping voices up to date for you.
List all available voices
Try this code to list all available voice within AudioStack: https://audiostack.readme.io/reference/listvoices
Below is a list of the voice providers you can currently render your text with. You can listen to an audio sample of each voice if you filter by provider here: https://library.audiostack.ai/
Eleven Labs
Eleven brings the most compelling, rich and lifelike American English voices to creators and publishers seeking the ultimate tools for storytelling. Eleven also offers STS (Speech to Speech).
OpenAI
OpenAI is a leading provider in AI tools, and most recently TTS voices with competitive naturalness and remarkable overall performance.
Cartesia
Cartesia is newcomer in the TTS field, offering hyper realistic and diverse voice options, as well as demonstrating impressive speed capabilities.
Play.HT
Play.HT offers natural sounding, humanlike voice performances across any language and accent.
Microsoft Azure
Azure offers a huge selection of voices in a multitude of languages. A number of them also support speaking styles such as cheerful, narration or sad.
Open Source
Did you know that a certain famous Astronomer's voice model is openly available for anyone to use?
Resemble.ai
Resemble is a Canadian boutique voice provider that builds voices for English. Resemble also offers STS (Speech to Speech).
WellSaid Labs
WellSaid offers a great selection of English voices with international accents across several speaking styles.
Respeecher
Respeecher is an Ukrainan TTS company that offers a selection of English voices with niche accents and STS capabilities.
Narakeet
Narakeet is a text to speech video maker that supports 100 languages and 700 voices.
Speechify
Speechify is a TTS provider with bespoke English accented voices, that vary in prosody and emotion.
Amazon Polly
Polly is Amazon's TTS brand and comes with a large number of voices in many languages
Cereproc
CereProc is a Scottish boutique voice provider, based in Edinburgh, the home of advanced speech synthesis research. It offers a wide range of voices across several languages
Google Wavenet
Google offers a huge range of text-to-speech voices across multiple languages. Within AudioStack you will find a selection of the best-sounding Wavenet voices.
IBM Watson
IBM Watson Text to Speech is an API cloud service that enables you to convert written text into natural-sounding audio in a variety of languages and voices.
Messner
Messner is AudioStack's internal voice cloning team. We offer custom voices, some of which are public and available on AudioStack for English.
Did you know?
You can use our Voice Intelligence Layer with a number of voices to improve the pronunciation of specific words and unify abbreviation recognition and date or time formats.
Updated about 2 months ago