Pay-as-you-go usage-based pricing with no commitments.$50 in Credits provided on signup, No Credit Card Required to start today. Rate-limits apply; get custom rate-limits with revenue commits. Additional costs apply for premium support. Please contact for details.
Get Started - Free Credit1. Platform usage is measured and billed per second but the invoices generated by our billing system report the usage in hours.
2. Each API request is subject to a minimum billing of 6 seconds and 1 second increment after that. An API request of 4 second is billed for 6 seconds or $0.0012 ($0.00020*6) and a real-time request for 7 seconds is billed $0.00020*7.
3. Basic model offers STT on a mono-channel with no Diarization or PII redaction. Enhanced model offers STT for two-channel call center audio (Agent and Caller on separate channels) It also includes Diarization (mono channel with multiple speakers) and PII Redaction.
4. STT Realtime-Basic and STT Realtime-Enhanced are for streaming audio over Web-socket. Basic is for mono channel with no diarization. Enhanced is for two-channel/stereo call center audio for call center application.
5. Telephony Bot API is an API to build telephony-based based AI Voice Agents. It includes Voicegain's IVR, Speech-to-Text, Text-to-Speech resources and it also includes the connector to LLMs and Chatbot frameworks.
6. MRCP ASR is the real-time Speech-to-Text/ASR as part of an MRCP Session. This price is applicable for the entire duration of the MRCP Session. It is does not include cost of 100% whole-call recording of sessions.
7. Rate Limits apply for pay as you go. We offer higher rate limits and lower pricing with volume & term commits. Please contact us at sales@voicegain.ai to get the details.
Deploy Voicegain on your private infrastructure. Free 30 day trial provided. Session/Port-based licensing. Port prices are paid yearly in advance while shown in the table as monthly. Minimum purchase of ports/usage is applicable. In addition, there is an Annual Support Cost. Discounted OEM pricing is available.
Contact Us1. Voicegain Edge refers to our platform being deployed on client's private infrastructure (Bare-metal, on VM or Virtual Private Cloud). Voicegain can be deployed using RPM-DEB, Docker Compose on VMs, OVA/OVF or on a Kubernetes Cluster.
2. For high throughput/concurrency, we recommend NVIDIA-GPU-based VMs or Kubernetes Clusters. CPU-based VMs are recommended for low concurrency use-cases. We also offer fully air gapped deployments where the Licensing Server is deployed in Client's datacaenter.
3. Client shall incur infrastructure costs and is responsible for monitoring resource usage of platform. For Private Cloud, we recommend managed Kubernetes from the cloud provider. For Datacenter, please contact us for support options.
4. "Port" - for STT Offline - is defined as throughput. So 25 Ports would allow offline transcription of 25 hours of offline audio per hour. For Real-time STT and MRCP ASR, Port is the number of concurrent Websocket sessions or MRCP Sessions respectively. E.g A 25-Port license would allow a maximum of 25 concurrent Websocket or MRCP Sessions.
5. MRCP Tier 1 provides access to our Grammar-based ASR. Voicegain supports grXML and JSGF grammars. Tier 2 provides access to our large vocabulary transcription.
5. For usage based licensing (STT-Offline & STT-Realtime), each request is subject to a minimum billing of 6 seconds and 1 second increment after that. E.g. a real-time request for 4 seconds shall be billed for 6 seconds or $0.0012 ($0.00020*6) and a real-time request for 7 seconds shall be billed for 7 seconds.
5. Voicegain offers discounts for volume & term commits. Please contact us at sales@voicegain.ai to receive custom pricing.
You can find the complete code (minus the RASA logic - you will have to supply your own) at our github repository.
The setup allows you to call a phone number and then interact with a Voicebot that uses RASA as the dialog logic engine.
November 2021 Update: We do not recommend S3 and AWS Lambda for a production setup. A more up to date review of various options to build a Voice Bot is described here. You should consider replacing the functionality of S3 and AWS Lambda with a web server that is able to maintain state - like Node.js or Python Flask.
The sequence diagram is provided below. Basically, the sequence of operations is as follows:
Interested in customizing the ASR or deploying Voicegain on your infrastructure?