Overview
ElevateAI APIs leverage cutting-edge research in artificial intelligence (AI), automatic speech recognition (ASR), and natural language processing (NLP) to transcribe audio conversations into precise text that can be fed into any data lake or application.
In addition, you can access key data needed to understand conversations at scale. CX AI provides objective insights into audio, transcription, and chat interactions, such as voice activity and out-of-the-box, industry-agnostic behavioral models (including sentiment analysis).
Getting started takes less than 60 seconds, and for each of the API endpoints you will find a tutorial outlining required parameters, code samples, and response examples / schemas.
You can transcribe and analyze audio interactions directly from the ElevateAI portal with no code needed.
We're here to help!
If you have any questions, our team of product experts and developers are available and eager to provide additional support!
Your active API tokens authorize requests on behalf of your account and carry many privileges, so be sure to keep them secure. Do not share your API tokens in publicly accessible areas such as GitHub, client-side code, etc.
To ensure authentication, all API requests must be made over HTTPS. Requests made over plain HTTP and/or API requests without an active API token will fail.
For your convenience and security, API tokens can be managed at any time in the Manage Tokens Dashboard.
Your data is yours!
The ElevateAI API is secured with Transport Layer Security (TLS) 1.2 to secure and encrypt the communication as well as protect the data in transit. The Service also uses TLS mutual authentication to ensure only legitimate users can access the API.
All source data is deleted promptly upon processing. Analysis output is stored in our US-based data warehouse for up to 45 days, encrypted in transit and at rest, so that you may access your results. After 45 days, all associated data is deleted and irretrievable.
If you have retrieved the desired results and would like to permanently delete all analysis data from our database prior to the 45-day standard retention period, you may do so at any time using the DELETE API endpoint.
As a publicly traded company trusted by leading brands worldwide, we make data security a top priority. See additional information in the ElevateAI Privacy Notice.
Remember: You can retrieve the processing status of your interaction at any time directly from a GET API endpoint or the Interactions Dashboard.
When declaring an audio interaction, you have the flexibility to prioritize for either highSpeed or highAccuracy.
Audio interactions prioritized for highSpeed are generally processed within 25-65% of the total interaction duration, but may vary by system integration and number of concurrent requests.
Audio interactions prioritized for highAccuracy may take up to twice as long to accommodate the latest in transformer technology for highest conversational accuracy.
Requests made where audioTranscriptionMode is set to highAccuracy may incur additional fees. See the the ElevateAI Invoicing Policy for more information.
Transcript and chat interactions are generally processed in seconds, but may vary by system integration and number of concurrent requests.
ElevateAI supports virtually all unencrypted audio types, whether single or dual channel. If you have any questions or would like to see a full list of supported audio files, reach out to us at support@elevateai.com.
Pro Tip: For highest levels of accuracy, we suggest stereo G.729A audio files.
ElevateAI supports both uploads and downloads up to 450MB.
| North American English | International English | Latin American Spanish | Brazilian Portuguese | Japanese |
languageTag | "en-us" | "en" | "es-419" | "pt-br" | "ja" |
Mono (single channel) | | | | | |
Stereo (dual channel) | | | | | |
vertical | "default" | "default" | "default" | "default" | "default" |
audioTranscriptionMode | "highSpeed" or "highAccuracy" | "highSpeed" or "highAccuracy" | "highSpeed" or "highAccuracy" | "highAccuracy" | "highAccuracy" |
PII Redaction | social security numbers, credit card numbers, and cvv numbers | credit card numbers and cvv numbers | social security numbers, credit card numbers, and cvv numbers | | |
Speaker Labels | diarization (mono), channel (stereo) | diarization (mono), ch |
| North American English | International English | Latin American Spanish | Brazilian Portuguese | Japanese |
languageTag | "en-us" | "en" | "es-419" | "pt-br" | "ja" |
| | | | | |
Composite Behavioral Scores | | | | | |
Behavioral Scores by Participant | | | | | |
| | | | | |
Acknowledge Loyalty | | | | | |
Active Listening | | | | | |
Be Empathetic | | | | | |
Build Rapport | | | | | |
Demonstrate Ownership | | | | | |
Effective Questioning | | | | | |
Inappropriate Action | | | | | |
Promote Self Service | | | | | |
Sentiment | | | | | |
Set Expectations | | | | | |
| | | | | |
Vulnerable Customer | | | | | |
Capability | | | | | |
Health | | | | | |
Life Event | | | | | |
Mental Health | | | | | |
Resilience | | | | | |
Financial Distress (BETA) | | | | | |
High Risk Transaction (BETA) | | | | | |
Churn | | | | | |
Complaint | | | | | |
Sales Effectiveness | | | | | |
ElevateAI uses conventional HTTP response codes for each API request. Codes in the 2xx range indicate the request successfully executed. Codes in the 4xx range indicate a failure based on the information provided (e.g., a required parameter was omitted). While rare, codes in the 5xx range may indicate an error with the ElevateAI service.
If a request is successful but an error occurs when uploading, downloading, or processing your interaction, a descriptive errorMessage will be provided when checking the processing status of the interaction.
We're here to help!
If you have any questions not addressed within this documentation, our team of product experts and developers are available and eager to provide additional support!
HTTP Status Code | Summary |
400 - Bad Request | The API request does not contain the expected parameters (either missing a required parameter or providing an unexpected value for a parameter). Prior to re-requesting, review the parameters and code examples within the associated tutorial. |
401 - Unauthorized | The API request is missing or passed an invalid X-API-Token in the header. Prior to re-requesting, confirm or request your API token within the Manage Tokens Dashboard. |
404 - Not Found | Either the API request was made with an invalid/deleted interactionIdentifer in the path, or analysis results have been requested prior to processing completion. Prior to re-requesting, confirm your API token within the Manage Tokens Dashboard, check the processing status. |
409 - Conflict | The API request made can't be complete because you have previously uploaded an audio file or provided a downloadUri when declaring the audio interaction. |
413 - Payload Too Large | The ElevateAI service couldn't retrieve the uploaded file or the file is larger than the maximum supported file size. Confirm file size, re-upload, and if you still receive the error, re-declare the interaction. |
429 - Too Many Requests | The API request to declare the interaction exceeds the monthly quota associated with your account. To upgrade to a paid account or request your quota be increased, contact us at sales@elevateai.com. |
Free accounts have access to declare up to 1000 interactions per day! If you are interested in upgrading to a paid account for higher usage, please contact us at sales@elevateai.com.
By default, paid accounts have access to declare up to 5,000 interactions per day.
If you require a higher limit, pleased reach out to us at support@elevateai.com to request this limit be increased.
Our team of product experts and developers are on-call and available to answer any questions you may have!
For fastest response times, please direct your question to the following:
Questions about upgrading to a paid account? Contact us at... | |
Questions about the terms of use, privacy policy, or the legal things? Contact us at... | |
Questions about our product roadmap or to request a feature? Contact us at... | |
For ANY OTHER support questions, contact us at... |