Hearing AI Pricing REST API & WEB UI
Each account is provided a modest amount of hearing compute that can be used through the speech to text web interface or for testing the implementation of the developer API. Costs for the use of Hearing AI and speech to text capabilities are determined by the duration of the transcribed audio and calculated accordingly.
Additional hearing compute can be added at any time using the account page which also displays the current balance of each compute.
- Dual-channel audio is treated as a single file. You will not be charged for dual-channel audio unless you submit each channel as an independent files.
- Hearing AI Speech to text is billed in one-second increments.
- All compute usage and costs of use will be calculated and displayed online. View Usage.
asticaListen v1.0_full offers accurate speech to text transcription of a live microphone or recorded audio capable of facilitating real-time integrations involving speech transcription.
asticaListen v2.0_full offers additional flexibility and training for non-vocal transcriptions such as coughing and laughs, and has the capability of transcribing advanced audio and media such as music. Optional natural language enables accurate and coherent transcription of industry-specific terminologies and acronyms.