Overview
26 min
// // introduction 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 using elevateai, you can access key data needed to understand conversations at scale our cx ai models provide objective insights into audio , transcription and chat interactions, such as voice activity, out of the box behavioral models – including sentiment analysis – and our elevateai generative ai api calls that includes autosummary, agent coaching, ask elevateai q\&a, and more new introducing echo by elevateai echo is elevateai’s next generation transcription model , now available for enterprise use designed for high accuracy speech recognition at scale, echo supports over 50 languages and dialects , making it ideal for global applications built with enterprise requirements in mind, echo delivers advanced transcription accuracy multilingual support optimized for diverse regional accents scalable performance for high volume workflows 🔗 view the full list of supported languages elevateai api information flow just getting started? get started in under 60 seconds! each api endpoint includes a detailed tutorial with required parameters, code samples, and response examples/schemas to help with your integration quickly and efficiently not a developer? you can transcribe and analyze audio interactions directly from the web based 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 information and support , as needed! // // authentication your active api tokens are used to authenticate requests on behalf of your account and grant access to a wide range of privileges to protect your data and systems keep your tokens secure at all times never share api tokens in publicly accessible locations, including public github repositories client side code forums or documentation 🔒 treat api tokens like passwords – exposing them can compromise your account note to ensure authentication, all api requests must be made over https requests made over 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 using the elevateai manage tokens dashboard / / / / data retention & security with elevateai, your data is yours ! api security the elevateai api is secured using transport layer security (tls) 1 2 , which encrypts all communication and protects data in transit to further enhance security, the service also supports tls mutual authentication , ensuring that only authorized clients 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 note 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 delete api endpoint as a publicly traded company trusted by leading brands worldwide, we make data security a top priority looking for additional information? please refer to the elevateai privacy notice // // processing times remember, you can retrieve the processing status of your interaction at any time directly from a get api endpoint or the interactions dashboard audio interaction files audio interactions are generally processed within 25 65% of the total file duration , but may vary by system integration and number of concurrent requests transcript and chat interaction files transcript transcript and chat chat interactions are generally processed in seconds , but may vary by system integration configuration and/or number of concurrent requests // // accepted file formats & sizes audio file formats elevateai supports virtually all unencrypted audio types, whether single or dual channel if you have questions or would like to see a full list of supported audio files, contact our support team at support\@elevateai com pro tip for highest levels of accuracy, we suggest stereo g 729a audio files supported file sizes elevateai supports both uploads and downloads up to 450mb // // transcription models & language capabilities what's new? echo by elevateai is our newest and most accurate transcription model, now available for enterprise use next gen echo transcription model our echo transcription model was designed for high accuracy speech recognition at scale , registering 40% accuracy increases over previous performance tests echo supports over 50 languages and dialects with automatic language detection , making it ideal for global applications built with enterprise requirements in mind, echo delivers advanced transcription accuracy multilingual support optimized for diverse regional accents scalable performance for high volume workflows 🔗 view the full list of echo's supported languages echo is ideal for all media types , including interviews, podcasts, videos, calls – and is optimized for contact center media and more! purpose built cx transcription model our original cx transcription model was purpose built for the contact center , leveraging decades of industry experience and billions of real customer interactions it delivers high accuracy transcription optimized for complex, multi speaker conversations across the contact center and a word error rate (wer) of less than 10% designed for cost efficiency and seamless integration , the cx model enables advanced customer sentiment analysis , empowering enterprises to improve compliance , quality assurance , and drive superior customer experience outcomes built for enterprise contact centers, the cx model delivers high accuracy transcription , tailored to customer service interactions advanced speaker diarization and multi speaker handling real time insights, powered by customer sentiment and behavioral analytics the cx model is ideal for all types of contact center media , providing affordable, scalable transcription that drives deeper cx intelligence and operational efficiency // // language support & model capabilities languages cx model our cx model supports the following languages language language language tag language tag pii redaction pii redaction north american english en us social security numbers; credit card numbers; cvv/cvc numbers international english en credit card numbers; cvv/cvc numbers latin american spanish es 419 social security numbers; credit card numbers; cvv/cvc numbers french fr german de brazilian pt br japanese ja cantonese zh yue mandarin zh cmn languages echo model the next generation echo transcription model offers automatic language detection and supports over fifty (50) languages and dialects , out of the box 🔗 🔗 view the full list of echo's supported languages languages cx ai models our cx ai models generate reportable ai scores for useful contact center metrics and behavioral insights languages supported by our custom cx ai models are noted below language language tag cx ai models north american english en us behaviors for csat ; sales effectiveness s s international english en behaviors for csat ; behaviors for vulnerable customers latin american spanish es 419 behaviors for csat brazilian portuguese pt br behaviors for csat language language tag cx ai models north american english en us behaviors for csat ; sales effectiveness international english en behaviors for csat ; behaviors for vulnerable customers latin american spanish es 419 behaviors for csat brazilian portuguese pt br behaviors for csat language language tag cx ai models north american english en us behaviors for csat ; sales effectiveness s s international english en behaviors for csat latin american spanish es 419 behaviors for csat languages generative ai our generative ai enpoints support all of the languages supported by our echo transcription model; click here to access the full list generative ai endpoints can be called in real time declare > immediately call generative ai for chats and transcripts audio files require processing to be completed prior to generatiove ai submission // // error handling elevateai uses conventional http response codes for each api request codes in the 2xx 2xx range indicate the request was 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 errormessage will be provided when checking the processing status of your interaction need additional assistance? visit the elevateai faq for more information – or contact support to get expert guidance tailored to your needs if you can't find what you're looking for in our documentation? our team of product specialists and engineers is always here to help contact us today ! 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 interactionidentifier 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 and check the processing status 409 – conflict the api request made can't be completed because you have previously uploaded an audio file or provided a downloadurl 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 e e 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 that your quota be increased – contact us at sales\@elevateai com // // daily quota free accounts free accounts have access to declare up to 1,000 interactions per day through elevateai's innovative 1k every day program! read more about 1k every day access elevateai pricing request a quote for enterprise pricing if you are interested in upgrading to a paid account to expand your elevateai usage, please contact us at sales\@elevateai com paid accounts by default, paid accounts have access to declare up to 5,000 interactions per day if you require a higher limit, please contact us at support\@elevateai com to request a limit increase // // additional support our team of product experts and developers are on call and here to help for specific inquiries, please reach out to the appropriate team sales & partnerships for enterprise pricing, high volume packages, tailored quotes, or partnerships, contact sales\@elevateai com product & technical for questions about transcription capabilities, model performance, or upcoming releases, contact support\@elevateai com legal & compliance for inquiries about our terms of use, privacy policy, or other legal matters, contact legal\@elevateai com general support for all other product, sales, or support related questions, contact support\@elevateai com