TEN-framework/ten-framework

[FEATURE] Voice assistant initially responds with a male voice; should switch to female voice as per configuration in Ten Agent

Open

#771 opened on Apr 29, 2025

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (10,605 stars) (1,282 forks)user submission
buggood first issue

Description

Description

When interacting with the voice assistant, the initial response is delivered in a male voice even though the configuration has been updated to use a female voice in the Ten Agent settings. The voice should immediately reflect the selected preference to ensure a consistent user experience.

Severity

Minor

Additional Information

Steps to Reproduce Start the voice assistant.

  1. Ask the first question — the response comes from a male voice.
  2. Change the voice configuration in the Ten Agent to female.
  3. Continue the conversation — the voice should switch immediately but doesn't.

Expected Behavior Once the voice configuration is changed to female in the Ten Agent, all subsequent responses from the voice assistant should be in a female voice.

Actual Behavior The voice assistant continues to respond in a male voice initially, and the switch to the configured female voice happens only after the first response or with a delay.

Image

Contributor guide

Tech stack
python
Domain
aibackend
Issue type
bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Familiarity with TEN framework voice configurationUnderstanding of TTS voice selection
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70
Research direction
Investigate the voice configuration loading and application logic in the TEN agent. Look at how the TTS voice is set initially and when the configuration change is applied. Focus on the code path that selects the voice model for the first response. Check if the configuration is read only at startup or if it can be updated mid session. The issue may be in the agent initialization order or caching of voice settings.