Issue Station
Sign In
Tools hereToolbox

openclaw - ✅(Solved) Fix [Bug]: TTS tool ignores edge.voice config [1 pull requests, 3 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#64153•Fetched 2026-04-11 06:16:15
View on GitHub
Comments
3
Participants
2
Timeline
5
Reactions
0
Author
ion-ctrlion-ctrl
Participants
ion-ctrlion-ctrlJah-yeeJah-yee
Timeline (top)
commented ×3cross-referenced ×1referenced ×1

Root Cause

From issue #57506: The tts tool is hardcoded to Edge TTS and does not read messages.tts config at all. The tool bypasses all configuration and calls Edge TTS directly with a fixed/default voice.

Fix Action

Fixed

PR fix notes

PR #64177: fix(tts): pass configured voice into tts tool

Description (problem / solution / changelog)

Summary

  • pass the resolved shared OpenClaw config into the built-in tool instead of only forwarding the optional per-call config
  • let the tool path honor the existing provider configuration, including Edge/Microsoft voice settings
  • add a focused regression test proving the tool receives the resolved shared config

Closes #64153

Testing

  • attempted:  ERR_PNPM_NO_IMPORTER_MANIFEST_FOUND  No package.json (or package.yaml, or package.json5) was found in "/root/.openclaw/workspace".
  • blocked locally in this worktree because / are unavailable ()
  • sending to CI for verification

Changed files

  • src/agents/openclaw-tools.ts (modified, +1/-1)
  • src/agents/openclaw-tools.tts-config.test.ts (added, +65/-0)

Code Example

messages.tts = {
  "auto": "always",
  "provider": "edge",
  "providers": {
    "edge": {
      "voice": "en-US-AvaNeural"
    }
  }
}
RAW_BUFFERClick to expand / collapse

Bug Description

The tts tool generates audio using a hardcoded default voice regardless of messages.tts.providers.edge.voice setting. Config changes to edge.voice have no audible effect.

Environment

  • OpenClaw version: 2026.4.9
  • OS: macOS
  • Channels affected: Matrix, Discord

Config Applied

messages.tts = {
  "auto": "always",
  "provider": "edge",
  "providers": {
    "edge": {
      "voice": "en-US-AvaNeural"
    }
  }
}

Tested with JennyNeural, AvaNeural — both produce identical audio. Voice setting is never used.

Expected Behavior

Setting messages.tts.providers.edge.voice should cause the tts tool to use that voice.

Root Cause

From issue #57506: The tts tool is hardcoded to Edge TTS and does not read messages.tts config at all. The tool bypasses all configuration and calls Edge TTS directly with a fixed/default voice.

Related

  • #57506 — [Bug]: TTS tool ignores messages.tts.openai.baseUrl — hardcoded to Edge TTS regardless of config (same root cause)
  • #61858 — [Feature]: Per-agent TTS voice/voiceId configuration

extent analysis

TL;DR

The tts tool is hardcoded to use a default voice and does not read the messages.tts.providers.edge.voice configuration, so a workaround or code change is needed to use a different voice.

Guidance

  • Review the code of the tts tool to identify where the hardcoded voice is set and consider modifying it to read the messages.tts.providers.edge.voice configuration.
  • Check the related issues (#57506 and #61858) for potential solutions or workarounds, as they seem to be related to the same root cause.
  • Consider reaching out to the maintainers of the tts tool or the OpenClaw project to report the issue and ask for assistance.
  • Verify that the messages.tts.providers.edge.voice configuration is correctly set and that the expected voice is supported by the Edge TTS provider.

Example

No code example is provided as the issue does not contain enough information about the codebase.

Notes

The fix may require modifying the tts tool or waiting for an update that addresses the hardcoded voice issue. The related issues may provide more information or potential solutions.

Recommendation

Apply a workaround, as the issue is caused by a hardcoded default voice in the tts tool, and upgrading to a fixed version is not mentioned as an option in the issue.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#logging issue#authentication issue#prompt issue#agent setup#task chaining

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING