AI-generated Answer for brothernumsy.
I'm sorry, but the information provided does not include specific details on how to configure Audiocodes to reduce latency. However, there are general methods for reducing streaming latency that might be helpful:
-
Use the Turbo v2.5 model: This model is designed for tasks that require extremely low latency.
-
Use the streaming API: The streaming endpoint streams back the audio as it is being generated, resulting in much lower response time from request to first byte of audio received.
-
Use the input streaming Websocket: This allows for prompts to be fed to the endpoint while the speech is being generated. You can also configure the streaming chunk size when using the websocket, with smaller chunks generally rendering faster.
-
Update to the Enterprise plan: Enterprise customers receive top priority in the rendering queue, which ensures that they always experience the lowest possible latency, regardless of model usage load.
-
Use Premade, Synthetic Voices & IVCs rather than PVCs: Default voices, synthetic voices, and Instant Voice Clones tend to have lower latency compared to Professional Voice Clones.
-
Reuse HTTPS Sessions When Streaming: When streaming through the websocket, reusing an established SSL/TLS session helps reduce latency by skipping the handshake process.
-
Leverage Servers Closer to the US: Users may experience latency from increased network routing when communicating with these APIs outside of the United States.
Please refer to the specific documentation or support resources for Audiocodes for more detailed instructions.
stable maple
wet turret