Frequently Asked Questions
Phebi makes it easy to better understand people better by detecting their unconscious emotions in quant, qual, and CX/UX research. It analyzes how people speak in recorded audios and videos, is an add-on to leading survey platforms for collecting and analyzing responses, and can be added to web conferences to analyze emotion in near real-time.
Here are answers to frequently asked questions to help you get started. If there’s anything else you’d like to know, contact us at info@phebi.ai.
What is Phebi?
Phebi is a leader in applied voice tech and emotional intelligence. Phebi’s award-winning software brings proven behavioral science research together with speech recognition, AI, and machine learning to provide a deep understanding of people’s nonconscious (emotional) responses. It’s used by agencies and brands in quantitative and qualitative health and market research, customer experience, and other applications to increase understanding, better predict behavior, and help improve business results.
Today, the software has two main parts:
– A software-as-a-service portal where you can quickly see people’s nonconscious responses in powerful new ways. You’ll realize immediate value from viewing summary reports and visualizations, including reports that automatically rank order concepts and products by emotional response, listening to audio and seeing the speaker’s emotion, reading transcriptions, getting emotion and sentiment scores, and using easy-to-understand tools to further explore the data, tag responses, create subgroups, and more. You can also download audio and video clips to better tell the story in the data. And, Phebi returns transcriptions to your market research platform and makes it easy for you to export the emotion scores and other information for additional analysis.
– Data collection via a simple add-on to any market research platform that makes it easy to voice-enable any survey. By enabling respondents to respond by speaking instead of typing, Phebi improves each respondent’s experience and generates longer, richer answers because when people talk instead of type they say more, especially on mobile. Phebi’s data collection can also be added to CATI surveys and Phebi Live (real-time emotional intelligence) can ‘call in’ to online meetings and be added to phone calls.
How does Phebi make survey and market research better?
Phebi uses speech recognition, AI, and machine learning to unlock what’s in people’s heads and hearts at scale. It’s used by agencies and brands in quantitative and qualitative health and market research, customer experience, and other applications to increase understanding, enhance storytelling, better predict behavior, and help inform better decisions that improve business results.
For example, imagine a voice-enabled survey of patients about a new medical treatment. Phebi scores the emotion in the spoken responses, identifying moments where people feel calm, anxious, happy, or sad. Responses are transcribed, reported on, and visualized. They can be played back; filtered by subgroup, topic, emotion, or other variables; and downloaded. All of this opens up new levels of understanding and enables better outcomes.
Why did Phebi develop this software?
Voice is the most intuitive, natural, and efficient way to communicate—talking is simply faster and easier than typing. It’s also an emotional microscope. When people speak they are likely to share more than when they type (4.5 times more, according to a recent study). And, their voices carry a wealth of previously inaccessible data about their emotional states as they speak.
Seeing consumers across demographics enthusiastically embrace voice as a part of modern life, our founders created Phebi to bust the trove of emotional insights wide open. Phebi enables researchers to benefit from the deeper insights voice uncovers—quickly, easily, and cost-effectively.
What data does Phebi make available to me? How is it available?
Phebi gives you the full picture. With it, you can learn what people said (speech-to-text transcription with separate results for each speaker), the implications of the words they used (sentiment analysis), and how they felt about the topic (emotion analysis). You can also listen to and download spoken responses and segments of recorded audio and video, and you can get automated reporting and, if you’d like to, further explore the data in a portal to which your team has unlimited access.
If you use Phebi to voice-enable a survey, transcriptions of spoken or videoed responses are automatically fed back into your survey platform in near real-time. Phebi also exports data for additional analysis in other software applications.
How does Phebi work technically?
Phebi is based on well-accepted behavioral science research about the relationship between characteristics of speaking voices, such as volume, rate, and tone, and the speaker’s underlying emotion. Phebi uses a combination of voice tech, AI, and advanced machine learning techniques to collect and analyze audio. Each speaker’s vocal characteristics are analyzed every 3 seconds based on a foundation that includes taking into consideration things like the norms for languages and genders to produce reliable, unbiased results.
Phebi’s innovative technology ‘stack’ was built from the ground up, trained, and tested at Phebi Labs, where it is continually being improved as our team works with new customers and in new applications, and proven in ‘research-on-research’ by research professionals at the leading agencies and global brands that are Phebi clients.
How do I add Phebi to a survey?
Phebi easily integrates with any survey software or online form so you can realize its value with no disruption to your current processes or project timelines. And, it works with all the supported versions of the major browsers. Your team (usually the people who do survey scripting) simply answers a few questions online and receives a small JavaScript and CSS plugin that is configured to your preferences for how your survey will deploy voice. Fast, friendly expert support is available.
What question types does Phebi support?
While Phebi can support most question types, it delivers the most value for open-ended questions as spoken responses to OEs are typically longer, richer, and quicker to provide, and the ability to respond via voice improves the respondents’ experience and perception of your brand.
Phebi is configurable via an online ‘check-the-box’ form that generates the code for survey scripters to copy and insert. For example, you can require that respondents answer via voice or give them the option to talk or type.
Typically, what percentage of survey respondents choose to respond via voice?
Each survey is different, but typically 40% to 60% of respondents choose to respond via voice when given the option of talking or typing. Phebi will work with you to use voice best practices to help you collect more emotionally rich data and to provide a brand-building user experience.
How does Phebi affect interview length?
With Phebi you get more data in less time. Based on research, responding to open-ended questions on mobile devices via voice is between 6 and 10 times faster than typing a response.
How do I use Phebi to analyze longer-form audio or video?
Phebi transcribes and analyzes audio and video files from focus groups, in-depth interviews, concept tests, etc. You simply select the files from wherever you’ve stored them to upload into Phebi, and the software does the rest.
How long does the analysis of audio or video files take?
Turnaround time varies based on file length. The transcription and analysis of a typical interview file are typically available in minutes.
Are there any limits or size restrictions related to using Phebi?
There are no limits or size restrictions related to using Phebi.
How does Phebi store data?
Phebi securely stores data on its own servers in an ISO-270001 certified data center. We have clusters in many countries to meet privacy requirements. Data are fully encrypted at rest and will be deleted in six months or based on timing that is agreed to with the Phebi customer or at the request of a consumer.
In which countries is Phebi available?
Phebi is available in any country not restricted by U.S., U.K., or EU law.
Does Phebi support any languages other than English?
Phebi currently supports English, Spanish, French, German, Dutch, Italian, Portuguese, Swedish, Finnish, Norwegian, Japanese, Cantonese, Mandarin, and Korean.
More languages are being added all the time. Transcription of the non-English languages listed above into English is done for a small fee.
How is Phebi priced?
Phebi’s pricing is based on the volume of audio or video processed; there are no ‘per seat’ charges for portal access. Phebi offers two pricing options: (1) pay-as-you-go, project-based pricing and (2) blocks of ‘credits’ to be used across multiple projects and to realize lower processing costs. Each Phebi credit can be used to process one open-ended response, up to 30-seconds of a longer-form audio file, or up to 15-seconds of long-form video. Phebi Live (real-time) is premium priced. Value-added reseller and referral arrangements are available.
Are there other ways to use Phebi technology?
Phebi is a leader in the emerging Voice Economy. In addition to our current offerings, which include an SDK and access via a WebSocket, we’re exploring other areas to apply our award-winning technology. You can propose new ideas to us here.