Voice-to-text conversion based on third party proxy content

The invention discloses voice-to-text conversion based on third-party proxy content, and relates to dynamic and context-sensitive biasing of voice-to-text conversion. In some implementations, the biasing of voice-to-text conversion is performed by a voice-to-text engine of a home agent, and the biasing is based at least in part on content provided to the home agent by a third party (3P) agent in network communication with the home agent. In some implementations, the content includes context parameters provided by the 3P agent in combination with response content generated by the 3P agent during a conversation between the 3P agent and a user of the voice-enabled electronic device; and assistance is realized by the local agent. The contextual parameters indicate potential characteristics of additional voice input to be provided in response to response content generated by the 3P agent. Embodiments reduce the use of various computing resources (e.g., network traffic that may be consumed by additional rounds nece