Give Your Agent a Voice
SkillSkill
ElevenLabs v3 to Telegram voice note pipeline. OGG Opus output skips FFmpeg entirely. Text engineering matters more than API settings.
About
A guide to wiring ElevenLabs v3 into an OpenClaw agent so it sends voice notes via Telegram, delivered as an inline voice bubble rather than a downloaded audio file.
Three things make this work that most tutorials do not cover. ElevenLabs v3 with Audio Tags is a different product from v2/multilingual: tags like [sigh], [laugh], and [excited] are parsed as performance direction and they work. ElevenLabs natively outputs OGG Opus at opus_48000_128, which is exactly what Telegram sendVoice requires. No FFmpeg, no audio conversion. Text engineering matters more than voice settings: punctuation, capitalisation, and pacing cues move performance more than any API slider.
Also covered: the Python SDK v2.x generator issue. The generate() function returns a generator, not bytes. Call b''.join(generator) before you have audio data. Every first-time implementation breaks here.
What is included: a complete async Python implementation, a text engineering guide with 8 techniques and examples, the Audio Tags reference, the sendVoice vs sendAudio distinction, and a troubleshooting section.
Best for OpenClaw operators who want their persona agents to send voice notes via Telegram.
Core Capabilities
- Complete async Python implementation: ElevenLabs v3 → Telegram sendVoice
- Text engineering guide: 8 techniques that control emotional performance
- Audio Tags reference: full list of v3-supported emotional direction tags
- OGG Opus native output setup — zero FFmpeg dependency
- Python SDK v2.x generator gotcha fix — the bug that breaks every tutorial
- sendVoice vs sendAudio distinction: inline voice bubble vs music player UI
Customer ratings
0 reviews
No ratings yet
- 5 star0
- 4 star0
- 3 star0
- 2 star0
- 1 star0
No reviews yet. Be the first buyer to share feedback.
Version History
This skill is actively maintained.
March 25, 2026
One-time purchase
$19
By continuing, you agree to the Buyer Terms of Service.
Creator
Melisia Archimedes
Creator
Melisia Archimedes is the architect behind the Hive Doctrine — a production-tested system for building, orchestrating, and running multi-agent AI teams. I've spent years in the field, not on the whiteboard. Every config, framework, and pattern I sell has run in a live production environment managing real workflows, real decisions, and real money. What's in the Hive Doctrine isn't theory — it's what survived contact with reality. My work spans agent identity design, memory architecture, multi-agent coordination, and the operator systems that hold everything together under pressure. The Pantheon agents — Marcus, Elliott, Elijah, Lila, Priya, and the rest — are production personas I built for my own operation and now make available to serious operators who want a real foundation instead of a blank prompt. If you're tired of starting from scratch every time, these configs will cut your setup time from weeks to hours and give you a system that actually holds together at scale.
View creator profile →Details
- Type
- Skill
- Category
- Content
- Price
- $19
- Version
- 1
- License
- One-time purchase
Works great with
Personas that pair well with this skill.
The Autonomous Content Engine — Ship 50 Posts/Week Without Touching a Keyboard
Persona
Complete blueprint for an AI content engine that posts daily across X, newsletters, Dev.to, and LinkedIn. Formula rotation, engagement tracking, and self-improving loop.
$29
Jasper Mason: Your AI Document Engineer
Persona
Absorbs large context fast, cleans up messy working material, and turns bulky source inputs into usable drafts, checklists, and implementation notes.
$49
Leo
AI Video Content Agent — Scripts, HeyGen avatar videos, editorial calendar on autopilot
Autonomous short-form video content: topic proposals, validated scripts, HeyGen video generation, 3x/week calendar.
$39