let5see/clawdbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(telegram-tts): add latency logging, status tracking, and unit tests

Browse Source 
- Add latency metrics to summarizeText and textToSpeech functions
- Add /tts_status command showing config and last attempt result
- Add /tts_summary command for feature flag control
- Fix atomic write to clean up temp file on rename failure
- Add timer.unref() to prevent blocking process shutdown
- Add unit tests for validation functions (13 tests)
- Update README with new commands and features

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Glucksberg
2026-01-24 03:12:37 +00:00
committed by Peter Steinberger
parent 4b24753be7
commit 104d977d12
3 changed files with 361 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
extensions/telegram-tts/README.md
View File

@@ -4,15 +4,18 @@ Automatic text-to-speech for chat responses using ElevenLabs or OpenAI.
## Features
- **Auto-TTS**: Automatically converts all text responses to voice when enabled
- **`speak` Tool**: Converts text to speech and sends as voice message
- **RPC Methods**: Control TTS via Gateway (`tts.status`, `tts.enable`, `tts.disable`, `tts.convert`, `tts.providers`)
- **User Preferences**: Persistent TTS state via JSON file
- **Multi-provider**: ElevenLabs and OpenAI TTS support
- **User Commands**: `/tts_on`, `/tts_off`, `/tts_provider`, `/tts_limit`, `/tts_summary`, `/tts_status`
- **Auto-Summarization**: Long texts are automatically summarized before TTS conversion
- **Multi-provider**: ElevenLabs and OpenAI TTS with automatic fallback
- **Self-contained**: No external CLI dependencies - calls APIs directly
## Requirements
- ElevenLabs API key OR OpenAI API key
- **For TTS**: ElevenLabs API key OR OpenAI API key
- **For Auto-Summarization**: OpenAI API key (uses gpt-4o-mini to summarize long texts)
## Installation
@@ -70,19 +73,20 @@ export OPENAI_API_KEY=your-api-key
| Option | Type | Default | Description |
|--------|------|---------|-------------|
| `enabled` | boolean | `false` | Enable the plugin |
| `provider` | string | `"elevenlabs"` | TTS provider (`elevenlabs` or `openai`) |
| `provider` | string | `"openai"` | TTS provider (`elevenlabs` or `openai`) |
| `elevenlabs.apiKey` | string | - | ElevenLabs API key |
| `elevenlabs.voiceId` | string | `"pMsXgVXv3BLzUgSXRplE"` | ElevenLabs Voice ID |
| `elevenlabs.modelId` | string | `"eleven_multilingual_v2"` | ElevenLabs Model ID |
| `openai.apiKey` | string | - | OpenAI API key |
| `openai.model` | string | `"tts-1"` | OpenAI model (`tts-1` or `tts-1-hd`) |
| `openai.model` | string | `"gpt-4o-mini-tts"` | OpenAI model (`gpt-4o-mini-tts`, `tts-1`, or `tts-1-hd`) |
| `openai.voice` | string | `"alloy"` | OpenAI voice |
| `prefsPath` | string | `~/clawd/.user-preferences.json` | User preferences file |
| `maxTextLength` | number | `4000` | Max characters for TTS |
| `timeoutMs` | number | `30000` | API request timeout in milliseconds |
### OpenAI Voices
Available voices: `alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`
Available voices: `alloy`, `ash`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`
## Usage
@@ -114,23 +118,28 @@ clawdbot gateway call tts.providers
### Telegram Commands
Add custom commands to toggle TTS mode:
The plugin registers the following commands automatically:
```json
{
"channels": {
"telegram": {
"customCommands": [
{"command": "tts_on", "description": "Enable voice responses"},
{"command": "tts_off", "description": "Disable voice responses"},
{"command": "audio", "description": "Send response as voice message"}
]
}
}
}
```
| Command | Description |
|---------|-------------|
| `/tts_on` | Enable auto-TTS for all responses |
| `/tts_off` | Disable auto-TTS |
| `/tts_provider [openai\|elevenlabs]` | Switch TTS provider (with fallback) |
| `/tts_limit [chars]` | Set max text length before summarization (default: 1500) |
| `/tts_summary [on\|off]` | Enable/disable auto-summarization for long texts |
| `/tts_status` | Show TTS status, config, and last attempt result |
Then add handling instructions to your agent workspace (CLAUDE.md or TOOLS.md).
## Auto-Summarization
When enabled (default), texts exceeding the configured limit are automatically summarized using OpenAI's gpt-4o-mini before TTS conversion. This ensures long responses can still be converted to audio.
**Requirements**: OpenAI API key must be configured for summarization to work, even if using ElevenLabs for TTS.
**Behavior**:
- Texts under the limit are converted directly
- Texts over the limit are summarized first, then converted
- If summarization is disabled (`/tts_summary off`), long texts are skipped (no audio)
- After summarization, a hard limit is applied to prevent oversized TTS requests
## License