AI voice & phone agent skills
Phone agents live or die on workflow: how to answer, when to transfer, how to confirm an appointment, what to do with voicemail. These skills encode call flows so a voice agent behaves like your best-trained hire.
The catalog here is young — this page grows as voice skills pass the pipeline. Everything listed carries the same scan, license and benchmark guarantees as the rest of the directory.
8 skills · 0 benchmarked with Lift · sorted by measured performance, then Trust.
Generates high-quality neural voiceover narration from text using Azure AI Speech, with voice, rate, pitch, and style control.
Transcribes audio or video files to text with word-level timestamps and speaker labels using Azure AI Speech Fast Transcription, with a local whisper
Generate music, soundtracks, jingles, or extract audio stems for video production.
Generates expressive multilingual text-to-speech narration using fish.audio models with support for cloned voices and inline emotion tags.
Generates Mandarin and multilingual narration audio using Volcengine Doubao Speech 2.0, with word-level timestamps for building subtitles.
Create AI-generated voiceovers, sound effects, and music using ElevenLabs APIs.
Generates voiceover, background music, sound effects, transcriptions, and captions for video compositions using a shared multi-provider audio engine.
Generates jingles, voiceover, and sound effects by routing music, speech, and SFX requests to appropriate audio models and saving the output as an MP3
FAQ
What is an AI receptionist skill?
An instruction pack that defines how a voice agent answers, qualifies, routes and takes messages — the conversational equivalent of a front-desk manual.
Do these place real calls?
The skills instruct; your telephony platform (LiveKit, Twilio, Vapi, Retell and similar) executes. The skill contributes the call flow, not the phone line.