Features
These features make it easy to build great audio experiences for your application.
SCRIPT - the piece of text you will turn to speech | Description |
---|---|
Text and audio management | API.audio makes it easy to create and administer (text) content in a way that is fit for creating audio. Individual content pieces (scripts) can be organised into modules and projects which are the base to efficiently mass version and produce audio. |
Dynamic Versioning | Personalize and localize your content using personalization variables to create content dynamically for different audiences. Turn a single script into thousands of different versions to address each of your audiences personally. Use sections to change voices, pair sound segments with your speech sections, add effects, adjust speed, or even add in your own uploaded media files. You can also use version flags to conveniently maintain different variants of the same script, such as different languages. |
SSML harmonization | SSML is the standardised markup language that allows to conveniently customize the speech of your audio. Using SSML in your text by providing details on pauses, intonation and pronunciation, gives you the control to enhance the speech you create. |
Predefined Scripts | API.audio's predefined scripts help ease your workflow by providing ready-made sample content for different use cases. |
Pronunciation Dictionary | Dictionary feature helps you fix the pronunciation of troublesome words. It will ensure that even the most unknown city names in the UK, brand names in german or last names of the United States will be pronounced in the correct way.You can also include your own brand specific dictionary to ensure that your company name is correctly pronounced in every audio created by your users. |
SPEECH | Description |
---|---|
Voice Library | API.audio's voice library includes over 600 voices from 8 different providers including our own in-house cloned voices (called messner). Find a voice for your use case in our library frontend library.api.audio. |
Voice Cloning | Clone a voice for your brand through our dedicated voice capture app. With at least 30 minutes of data you can get a clone of your voice to use through the API. |
Voice Upload | Upload your own recorded speech files, mix them with sound design and render directly through our API for professional sounding audio. |
Voice Discoverability | Our intelligent filtering system makes it easy for you to find voices that span across different languages, gender, accents and age groups. This will make it easy for you to offer your users the ability to find their favorite voice. |
Voice Effects | Use voice effects to alter the sound of your speakers voice. Make them sound like a famous cartoon character, alien or a chipmunk. With the immersive sound feature you can take your speaker from a loud underground bar to an ambient Parisian Cafe. |
Multi-Voice Speech | Using your own uploaded media files you can stitch together speech using your own recorded speech and any of our hundreds of voices. Make your own voice talk to Einstein or make your audio content even more personal by using your own recorded speech. |
Visemes & Facial Landmarks | Visemes are the visual representation of the face and mouth when speaking a word and different components of speech. Sync your speech over a virtual avatar conveniently by using visemes. |
Real-time speech | Real-time Text-to-Speech rendering. Use any of API.audio's library of voices to create speech from text in milliseconds. Best for conversational, real-time use cases. |
SOUND - sound collection to enhance your audio | Description |
---|---|
Sound Design | Sound design automation makes sure that the music layer will always fit perfectly to the speech layer of your audio, regardless of the length. |
Generative music * | Generate sound designs for each specific case by choosing the mood and style. Our sound engine will create a custom sound template for you. |
Sound Discoverability | API.audio's sound design library offers a selection of different sounds covering a range of common themes or use cases. Filter to find the perfect template for your use case. Choose from our library of sound templates and mix and master it along with your speech track to create beautiful audio programmatically in a matter of seconds. |
Sound Upload * | Upload your own sound files into API.audio. Use them over your speech and create beautiful audio that aligns with your brand. |
Time and length alignment | Set the length of each section of your audio to end at a specific time. For example you might want your ad to be exactly 30 seconds long or you might want your audio to fit to specific transitions in your video. |
PRODUCTION - post processing of audio to make it sound professionally produced | Description |
---|---|
Audio Mastering | API.audio allows you to programatically master your audio without any expertise about the process. Mastering allows you to create an audio file that is ready to be played or broadcasted. A mastered version contains the speech of the script, a sound design, and a mastering process to enhance the audio quality of the whole track. |
Scalable rendering | Our fast, scalable and well-performant mastering engine mixes multiple audio files together seamlessly. |
Mastering formats | Post production presets format your audio to be optimised for different platforms and use cases. Use the Spotify preset to have your audio formatted to meet Spotify's requirements or use the Audio ad preset that turns your script into a professional studio-quality ad. |
Audio Formats | API.audio offers a selection of different audio formats. Get your audio file in wav format that is perfect for further processing or in high quality mp3 that is the best quality for most situations and use cases. |
SCALE Features | Description |
---|---|
Input integrations * | Input connectors allow you to conveniently create content directly from the source. |
Output integrations | Output connectors allow you to easily share the audio created through API.audio on various channels. |
Dashboard | View and manage your data, upgrade your plan and have an overview of monthly usage. You'll also have access to everything from API logs to account settings and support. |
Roles and Permissions | Tailor data access of your team to ensure that each person has access to the right information. Keep track of recent activity across all your team members and get the most up to date information on produced content and analytics. |
Cache 'Birdcache' | Store your audio files in our servers and retrieve them on the fly. Produce audio for hundreds of different combinations with a single call, those files will then be stored and available for you to retrieve in the future in real time. |
Bulk Production * | Bulk process thousands of files in one go. |
Webhook * | A webhook enables you to receive your file produced through api.audio in real time to your application. API.audio uses HTTPS to send those notifications to your app as a JSON payload. |
Python and JS SDK | Use our native and performant libraries. The SDKs provide easy access to the API from applications written in Javascript or Python. |
*coming soon
Didn't find the feature you're looking for?
Contact [email protected]
Client Libraries:
More coming soon!
Updated about 2 years ago