Pocket FM Leverages AI to Rapidly Produce Engaging Audio Series, Aiming for Netflix-like Success

Audio streaming platform Pocket FM, based in India, aims to emulate the success of Netflix in the audio realm. To achieve this, the company plans to tailor its audio series offerings to suit individual user preferences by rapidly releasing content. To facilitate this rapid release, Pocket FM is incorporating AI tools into its creative process.

The venture-backed startup provides its writers with an AI toolkit capable of suggesting improvements such as more engaging narratives and better episode endings. The goal is to streamline the story-writing process.

Pocket FM has already employed AI tools like ElevenLabs for generating voices for audio series, and it has internally tested AI tools for writing and adaptation assistance.

CoPilot, Pocket FM’s new writing tool, assists writers in creating stories and transforming narrative-based writing into dialog-based writing for specific segments. It also performs “beat analysis” to shape the writing in a way that enhances engagement for audio series within a particular genre. Additionally, it offers basic chatbot-style features such as “shorten,” “expand,” and the ability to generate text via a prompt.

To develop CoPilot, Pocket FM analyzed thousands of hours of data points to understand what keeps users engaged with specific storylines in various genres. Based on this analysis, the tool incorporates writing suggestion features designed to increase conflict between characters and recommend exciting episode endings. AI can also suggest background effects tags for use during audio production.

CoPilot automatically generates character bios, relationship summaries, and plots of different episodes, providing creators with a convenient reference during the writing process. The tool also includes a review feature that checks for plot points, grammar, and provides qualitative feedback through comments on an episode.

In addition to AI tools, Pocket FM has developed adaptation tools for various markets. These tools not only translate text from one language to another but also modify names and phrases suitable for the specific region’s culture.

Pocket FM initially introduced this tool as part of the CoPilot suite in Germany earlier this year, aimed at converting stories from other regions following difficulties in engaging users in Europe last year. The company reported positive results from the trial, with monthly in-app revenue exceeding $700,000 in June.

In the U.S., series created using these new AI tools contribute 10% of playtime and have generated $7 million in revenue over the past 12 months while reducing production costs by two to three times. As a result of adopting various AI features, Pocket FM has been able to scale its content quickly, launching around 1,000 pilots per month.

Beyond audio shows, Pocket FM is working on tools to convert stories into comic strips through the Pocket Toons platform and exploring video as a possible format. The startup, which has raised over $196 million in funding across rounds, is also experimenting with a micro drama app.

By next year, Pocket FM plans to release its own large language model (LLM), based on data collected from its shows and incorporating various tools like writing assistance, adaptation, dramatization, and story context retention. When it switches to its own LLM, the company expects not to need to train numerous small models for separate features.

The adoption of AI has presented some challenges, including layoffs and concerns about quality. However, Pocket FM maintains that AI tools speed up a writer’s work and help them make targeted improvements based on numbers and audience feedback rather than complete rewrites. By doing so, the company believes faster content creation does not necessarily compromise quality or relevance; it simply shifts the writer’s role towards editing, refining, and steering more productive output.