skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

elevenlabs-dialogue

Generate multi-speaker dialogue audio from text scripts using ElevenLabs voices via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#podcast#audio generation#elevenlabs#voice acting#text to speech#dialogue generation#multi-speaker
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill elevenlabs-dialogue-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: elevenlabs-dialogue
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/elevenlabs-dialogue
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill elevenlabs-dialogue-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating multi-voice conversation audio for podcasts, audiobooks, or training content normally requires recording multiple voice actors or stitching together separate TTS clips. This Skill generates a complete multi-speaker dialogue in a single audio file from a simple text script. ## Core Features & Use Cases - Multi-Voice Dialogue Generation: Assign different voices to each segment of a script and produce one combined audio file with 22+ premium voices. - Voice Direction: Control delivery with inline direction tags like [excitedly], [whispering], or [sarcastically] for expressive, natural-sounding speech. - Use Case: A content creator writing a podcast episode can define segments with a host voice (george) and guest voice (aria), run one command, and receive a finished conversation audio file ready to mix with background music. ## Quick Start Ask the AI to generate a dialogue audio file using the elevenlabs text-to-dialogue app with your script segments and chosen voices, for example a two-person podcast intro with george and aria.

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 the belt CLI command 'belt app run elevenlabs/text-to-dialogue' with a JSON input containing segments, where each segment specifies text and a voice name. The output is a single audio file combining all speakers.

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

Over 22 premium voices are available, including female voices like aria, alice, bella, and sarah, and male voices like george, adam, brian, and daniel. Each segment in the script can use a different voice.

Can I control the emotion or tone of AI-generated dialogue?▼

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

Does elevenlabs text-to-dialogue require any setup or authentication?▼

Yes, it requires the inference.sh CLI (belt) installed and authenticated via 'belt login'. After login, you can run the text-to-dialogue app directly from the command line.

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

The dialogue-audio skill uses Dia TTS with S1/S2 speaker tags as a free alternative for multi-speaker generation. ElevenLabs offers more voices and direction controls but requires an inference.sh account.

Related Skills

Explore More Content & Communication Skills→
alchaincyfalchaincyf
1.3k

video-script-colloquial-proofreading

Convert formal video scripts into colloquial, on-camera language.

Community
Intermediate
massgenmassgen
1.1k

audio-generation

Generate speech, music, and sound effects using ElevenLabs and OpenAI audio APIs.

Official
Advanced
inference-shinference-sh
688

ai-podcast-creation

Generate podcasts by synthesizing text-to-speech audio, composing music, and merging audio elements.

Official
Intermediate
inference-shinference-sh
688

text-to-speech

Convert text into speech using multiple TTS models like Kokoro TTS.

Official
Intermediate