Why data storytelling is crucial today
narrativesthat guide audiences toward concrete actions. Large Language Models (LLMs) have become essential tools for automating the creation of these stories, enabling you to transform raw data into a structured narrative in just minutes.
New LLMs are revolutionizing the process
The latest models released this October demonstrate how rapidly data storytelling is evolving:
- Dessa
- Hermit
- Nemotron 3.5 Transcribe
By integrating these models into your workflows, you can accelerate the storytelling process and reach a broader audience.
The practical 5-step workflow
Start by uploading your dataset (CSV, Excel, or database). Use a small Python script to normalize it and remove irrelevant columns.
Create a prompt that asks the LLM to summarize trends, anomalies, and strengths in simple language.
prompt = """
Analyze the following sales dataset and produce a narrative paragraph suitable for a non-technical audience.
- Highlight the main trends over time.
- Identify the best-performing region.
- Suggest a possible next action.
Data:
{df.to_string(index=False)}
"""Use Hermit to add a layer of instructions that transforms the raw summary into a narrative skeleton: introduction, body, conclusion, and a catchy title.
Combine the text with a visualization. Tools like Tableau or Plotly can be triggered via prompt to generate charts that the LLM can then describe.
Run a feedback loop: the LLM can adjust tone, length, and level of detail based on the target audience. Once ready, export the story as a web page, PDF, or presentation.
Complete prompt engineering example
Below is a ready-to-use prompt that combines a text LLM with a speech model like Dessa for voice narration.
story_prompt = """
You are an expert data analyst. Write an engaging story about this year's sales, suitable for a boardroom audience.
Structure:
1. Title
2. Subtitle (1 sentence)
3. Intro (2 sentences that frame the context)
4. Main section with 3 bullet points, each with a brief description
5. Conclusion with a call to action
Input data: {df.to_string(index=False)}
"""
# Use the LLM to generate the story
story = llm.invoke(story_prompt)
# Convert the story to audio with Dessa (example API call)
audio_response = speech_model.generate(story, voice='Dessa')Key points to remember
- Select data carefully.Less noise means clearer stories.
- Use explicit prompts.Ask the LLM to follow a precise structure for consistency.
- Experiment with new models.Dessa for voice narration, Hermit for agentic workflow, Nemotron for multilingual transcription.
- Iterate based on feedback.Adapt tone, depth, and level of detail as the audience interacts.
Conclusion
Next steps
1. Choose a small dataset and apply the preparation script. 2. Create the summary prompt and test it with an open-source LLM. 3. Add a Hermit layer to structure the story. 4. Distribute a voice version with Dessa for a remote audience.
**IMPORTANT:** We are in 2026. All temporal references must be current. Do not mention past years like 2024, 2023, etc. The content must be fresh and relevant to the present. **CURRENT CONTEXT (October 2026):** Here are some recent trends and news to inspire you: - AssemblyAI Ships AssemblyAI-TTS-1: A $15 per 1M Character Text-to-Speech API for Voice Agents: AssemblyAI has released AssemblyAI-TTS-1, its first text-to-speech model for voice agents. It costs $15 per 1M characters, offers unlimited concurrency... [2026-10-29] - NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language Transcription with ~4B Active Parameters: NVIDIA released Nemotron 3.5 Transcribe, an open-weights speech LLM with 4.3B active parameters. It transcribes 40 languages, adds speaker labels and ... [2026-10-29] - Infini-AI-Lab Releases Hermit, an Open-Source Harness Adapter Framework for AI Agents: Infini-AI-Lab released Hermit, an Apache-2.0 harness adapter framework that trains an external layer of instructions, skills, memory and tools from ... [2026-10-29] Use this current information as inspiration to create an original and relevant prompt for 2026.