openclaw - ✅(Solved) Fix v2026.4.5: Telegram voice messages no longer transcribed (STT regression) [1 pull requests, 1 comments, 2 participants]

openclaw2026-04-07 00:19:54

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.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

openclaw/openclaw#62205•Fetched 2026-04-08 03:07:40

View on GitHub

Comments

Participants

Timeline

Reactions

Author

jhsmith409

Participants

jhsmith409

neeravmakwana

Timeline (top)

referenced ×5closed ×1commented ×1cross-referenced ×1

Voice message transcription (STT) stopped working after upgrading from v2026.4.2 → v2026.4.5. Telegram voice messages are no longer transcribed by the configured audio provider; the model receives the raw audio file instead.

Root Cause

Root Cause (traced through compiled source)

Fix Action

Workaround

Add "openai" to plugins.allow in openclaw.json:

"plugins": {
  "allow": ["...", "openai"]
}

This allows the openai bundled plugin to load, which registers openaiMediaUnderstandingProvider with transcribeAudio. The configured tools.media.audio.models[0].baseUrl correctly overrides the default api.openai.com URL, so a local OpenAI-compatible endpoint (e.g. Parakeet) works as expected.

Also required: a models.providers.openai entry with apiKey so resolveUsableCustomProviderApiKey can return a key for requireApiKey:

"models": {
  "providers": {
    "openai": {
      "apiKey": "local",
      "baseUrl": "<your local STT endpoint>/v1",
      "models": []
    }
  }
}

Code Example

if (params.config.allow.length > 0 && !explicitlyAllowed) return {
    enabled: false,
    reason: "not in allowlist"
};

---

"plugins": {
  "allow": ["...", "openai"]
}

---

"models": {
  "providers": {
    "openai": {
      "apiKey": "local",
      "baseUrl": "<your local STT endpoint>/v1",
      "models": []
    }
  }
}

RAW_BUFFERClick to expand / collapse

Summary

Environment

OpenClaw version: v2026.4.5
Channel: Telegram (DM)
STT provider: OpenAI-compatible endpoint (Parakeet / NVIDIA NeMo at a local URL)
Config: tools.media.audio.models[0].provider = "openai", tools.media.audio.models[0].baseUrl = <local Parakeet URL>

Behavior

v2026.4.2: Voice messages were transcribed correctly; echoTranscript fired (🎤 echo sent to user before agent reply).

v2026.4.5: No echo sent; model receives raw audio file; agent responds generically instead of to the voice content.

Root Cause (traced through compiled source)

In v2026.4.5, Telegram voice handling routes through applyMediaUnderstanding (apply-CU6lCv5P.js), which builds a media understanding provider registry via buildMediaUnderstandingRegistry (provider-registry-Qp9sisqM.js).

The openaiMediaUnderstandingProvider (in media-understanding-provider-BUTtadCJ.js) provides transcribeAudio and is the correct handler for provider: "openai" audio entries. However, it only gets registered if the "openai" bundled plugin is active.

The activation check in manifest-registry-Cqdpf6fh.js (resolvePluginActivationState) contains:

if (params.config.allow.length > 0 && !explicitlyAllowed) return {
    enabled: false,
    reason: "not in allowlist"
};

If a user has a non-empty plugins.allow list that doesn't include "openai", the openai bundled plugin is blocked — even though it's enabledByDefault: true and the user has a valid tools.media.audio config using the openai-compatible API.

The compat fallback in capability-provider-runtime-CMlMeixn.js (resolvePluginCapabilityProviders → withBundledPluginEnablementCompat) is supposed to handle this, but it only adds to plugins.entries (not plugins.allow), so the allowlist check still blocks activation.

The result: getMediaUnderstandingProvider("openai", providerRegistry) returns undefined, causing runProviderEntry to throw "Media provider not available: openai" (silently caught in runAttachmentEntries). No audio.transcription outputs are produced, echoTranscript never fires, and the raw audio file is passed to the model.

Workaround

Add "openai" to plugins.allow in openclaw.json:

"plugins": {
  "allow": ["...", "openai"]
}

Also required: a models.providers.openai entry with apiKey so resolveUsableCustomProviderApiKey can return a key for requireApiKey:

"models": {
  "providers": {
    "openai": {
      "apiKey": "local",
      "baseUrl": "<your local STT endpoint>/v1",
      "models": []
    }
  }
}

Expected Behavior

Users with a configured tools.media.audio using provider: "openai" should not need to manually add "openai" to plugins.allow. The audio pipeline should work regardless of whether the openai provider plugin is explicitly allowed, since the user has an explicit audio model config that references it.

The withBundledPluginEnablementCompat compat path should either also add the plugin to plugins.allow, or the allowlist check should be skipped for bundled plugins that are required by an explicit capability config entry.

extent analysis

TL;DR

Add "openai" to plugins.allow in openclaw.json to enable the openai bundled plugin and restore voice message transcription.

Guidance

Verify that the tools.media.audio config is correctly set to use the openai-compatible provider by checking tools.media.audio.models[0].provider and tools.media.audio.models[0].baseUrl.
Add "openai" to plugins.allow in openclaw.json to allow the openai bundled plugin to load and register the openaiMediaUnderstandingProvider.
Ensure a models.providers.openai entry with apiKey is present in the config to enable the resolveUsableCustomProviderApiKey function to return a key for requireApiKey.
Test voice message transcription after applying the workaround to verify that echoTranscript fires and the model responds to the voice content.

Example

"plugins": {
  "allow": ["...", "openai"]
}

"models": {
  "providers": {
    "openai": {
      "apiKey": "local",
      "baseUrl": "<your local STT endpoint>/v1",
      "models": []
    }
  }
}

Notes

This workaround assumes that the user has a valid tools.media.audio config using the openai-compatible API. The long-term solution would involve updating the withBundledPluginEnablementCompat compat path to handle bundled plugins required by explicit capability config entries.

Recommendation

Apply the workaround by adding "openai" to plugins.allow in openclaw.json, as this allows the openai bundled plugin to load and register the openaiMediaUnderstandingProvider, restoring voice message transcription.

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?

#api #authentication setup #request error #file not found #serialization error

Still need to ship something?

×6

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

openclaw - ✅(Solved) Fix v2026.4.5: Telegram voice messages no longer transcribed (STT regression) [1 pull requests, 1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Root Cause

Root Cause (traced through compiled source)

Fix Action

Workaround

PR fix notes

PR #62234: Plugins: allowlist compat for capability provider fallback (#62205)

Description (problem / solution / changelog)

Summary

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Root Cause (if applicable)

Regression Test Plan (if applicable)

User-visible / Behavior Changes

Diagram (if applicable)

Security Impact (required)

Verification

Changed files

Code Example

Summary

Environment

Behavior

Root Cause (traced through compiled source)

Workaround

Expected Behavior

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING