skills.rest
inference-sh
inference-shOFFICIAL
Explore all skills by this author →
WebsiteGitHub

elevenlabs-dialogue

Generate multi-speaker dialogue audio with ElevenLabs voices via the inference.sh CLI.

723|101|Updated Jan 31, 2026
Search Tags:#podcast#ElevenLabs#voice acting#inference.sh#text to speech#dialogue generation#multi-speaker audio
One-click install
npx skills add https://github.com/inference-sh/skills --skill elevenlabs-dialogue
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs-dialogue
Source: https://github.com/inference-sh/skills/tree/main/tools/audio/elevenlabs-dialogue
Command: npx skills add https://github.com/inference-sh/skills --skill elevenlabs-dialogue

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating natural-sounding multi-speaker audio for podcasts, audiobooks, or training content normally requires recording multiple voice actors or stitching together separate TTS clips. This Skill generates complete conversations with distinct voices in a single audio file through one CLI command.

Core Features & Use Cases

  • Multi-Voice Dialogue Generation: Produce conversations using 22+ ElevenLabs voices (male and female) assigned per segment via the elevenlabs/text-to-dialogue app.
  • Voice Direction Tags: Control delivery with bracketed directions like [excitedly], [whispering], or [sarcastically] for expressive speech.
  • Script-Based Input: Define dialogue as structured JSON segments with text and voice fields for predictable, repeatable output.
  • Use Case: A podcaster writes a six-line interview script, assigns george and aria as speakers, and receives a ready-to-use episode intro audio file in one command.

Quick Start

Ask the AI to generate a dialogue audio file using the elevenlabs text-to-dialogue app with two voices, for example george and aria, reading a short welcome exchange.

Frequently Asked Questions about elevenlabs-dialogue

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate multi-speaker dialogue audio with ElevenLabs?▼

Run `belt app run elevenlabs/text-to-dialogue` with a JSON input containing a segments array, where each segment has a text field and a voice field. The output is a single audio file with all speakers combined.

What voices are available for ElevenLabs text-to-dialogue?▼

Over 22 voices are available, including female voices like aria, alice, bella, and sarah, and male voices like george, adam, brian, and daniel. Assign any voice to any segment in the script.

Can I control the emotion or tone of ElevenLabs dialogue voices?▼

Yes, add direction keywords in square brackets before the text, such as [excitedly], [whispering], [sadly], or [sarcastically]. Use one or two per exchange for natural-sounding delivery.

Does elevenlabs-dialogue work without the belt CLI installed?▼

No, the skill requires the inference.sh belt CLI installed and authenticated via `belt login`. Install instructions are available in the repository's cli-install.md file.

What is a free alternative to ElevenLabs for dialogue generation?▼

The repository offers a Dia TTS dialogue skill (dialogue-audio) that uses S1/S2 speaker tags as a free alternative. It suits simpler two-speaker scenarios without premium voice options.

Related Skills

Explore More Content & Communication Skills→
augustsclaugustscl
2

tts

Convert text to spoken audio via MP3 streaming or JSON audioUrl output.

Community
Advanced
RomainGRAS42RomainGRAS42

ai-podcast-creation

Generate AI podcasts and audio content with text-to-speech and media merging.

Community
Intermediate
JStaRFilmsJStaRFilms
23

ai-podcast-creation

Automate end-to-end AI podcast production from script to final episode.

Community
Advanced
maximoseomaximoseo

dialogue-audio

Generate two-speaker dialogue audio with Dia TTS using [S1] and [S2] tags.

Community
Advanced