Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    NongBank Voice Director

    1

    Direct multilingual narration and two-speaker dialogue. Cast voices, preserve language switches, and preview the render price in your agent.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    NongBank Voice Director

    Example session with this skill installed

    Plan a two-speaker podcast intro. Keep each line as written and do not generate audio yet.
    Amina: أهلاً بكم في حلقة اليوم.
    Rafael: Bienvenidos. Hoy hablamos de cómo cambia una ciudad al anochecer.

    • Read your context and instructions
    • Compiled the nongbank voice director

    Bilingual podcast intro — voice plan

    This example demonstrates planning mode.

    OrderSpeakerLanguageDirection
    1AminaArabicWarm welcome, measured pace, and a short pause at the end.
    2RafaelSpanishConversational energy with a gentle lift at the start and a steady finish.

    Lines to record

    1. Amina — أهلاً بكم في حلقة اليوم.
    2. Rafael — Bienvenidos. Hoy hablamos de cómo cambia una ciudad al anochecer.

    Render plan

    Choose two distinct catalog voices. Check whether the attached dialogue tool supports both languages in one MP3. If the available tools require separate clips, present that option first. When the buyer requests audio, quote the exact request before rendering.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Turn scripts into voiceover plans and audio for narration, dubbing, podcasts, and two-speaker dialogue.

    • Direct the performance. Choose from martial-arts dubbing, playful animation, cinematic openings, documentary narration, or podcast dialogue. Set a voice, pace, and emotional direction for each speaker.
    • Keep the script intact. Preserve names, punctuation, speaker order, and language switches. Review locale and pronunciation choices before rendering.
    • Render in your agent. Use the attached ElevenLabs tools through Agensi. The skill checks available languages, voices, and file formats, then shows a quote. Audio usage charges are separate from the one-time skill purchase.

    Language and accent coverage depend on the available model and voice. A compatible dialogue tool can return one audio file. Some requests may require separate ordered clips. The skill uses catalog voices.

    Audio rendering requires a connected Agensi account and a tool that supports the requested languages, voices, and format. Mixed-language pronunciation and regional accents vary by model. Dialogue may require separate clips. This edition uses catalog voices.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    Permissions

    No special permissions declared or detected

    Listed5 days ago

    What's inside

    Frequently Asked Questions

    Yes. It can prepare a plan for one narrator or two distinct speakers. When the selected Agensi dialogue tool supports the request, it can render one audio file. Otherwise it can propose ordered clips.

    Audio uses the ElevenLabs tools attached to the listing through your Agensi connection and tool balance. No separate provider key is required.

    Yes. The skill preserves the original text and checks language and voice support before quoting. If a selected model cannot handle an in-line switch, the skill offers a supported option and explains any change to the output.

    The skill asks Agensi for a quote based on the actual render and shows it before generation. Tool usage charges are separate from the one-time skill purchase.

    Use an MCP-compatible agent connected to Agensi. You can request a voice plan before deciding whether to render audio.

    This edition directs reads with catalog voices. It does not include the local Thai F5 voice clone engine.

    New in Image & Video