Spoken.md provides an API for retrieving podcast episode transcripts, searchable by title or guest, and delivered in Markdown format with speaker names and timestamps.
Why it matters
API Docs
API Available
overview
Spoken.md is an AI tool that enables podcasters and developers to retrieve transcripts for podcast episodes. It offers an API that allows users to search for episodes by title or guest and receive transcripts formatted in Markdown, complete with speaker names and timestamps.
features
Spoken.md is designed to provide structured podcast transcript data through its API, focusing on ease of integration and specific formatting requirements.
use cases
Spoken.md is primarily targeted at developers and podcasters who require programmatic access to podcast content for various applications and integrations.
how to use
To begin using Spoken.md, users typically access its API to search for and retrieve podcast transcripts. The process involves obtaining API credentials and making requests to the specified endpoints.
pricing
Spoken.md operates on a usage-based pricing model, where users purchase credits that do not expire. One credit is equivalent to one podcast episode transcript, regardless of its length. Failed API calls are not charged, and re-fetching an already pulled episode is free.
Enjoying this? Get one like it in your inbox each morning.
one email a day · unsubscribe in two clicks · no third-party tracking
Similar Tools
Spoken.md differentiates itself from general-purpose speech-to-text services by offering direct podcast search capabilities and pre-formatted Markdown output.
Offers a comprehensive Speech-to-Text API with advanced AI features like speaker diarization, content moderation, and summarization.
Unlike Spoken.md, AssemblyAI is a general-purpose transcription API; you provide the audio URL directly rather than searching by podcast title or guest. You would need to handle the Markdown formatting yourself from the API's JSON output.
Provides a highly accurate and fast Speech-to-Text API optimized for real-time and batch processing, with features like speaker diarization and custom vocabulary.
Similar to AssemblyAI, Deepgram requires you to supply the podcast audio URL directly, lacking Spoken.md's built-in podcast search functionality. You would also need to convert the API's output into Markdown format.
An open-source neural network for robust speech recognition, capable of transcribing audio in multiple languages and translating them into English.
Whisper is a model, not a hosted service with an API; it requires technical setup to run locally or via a community-built wrapper, and speaker diarization often needs additional tools. It does not offer podcast search by title/guest, and you would need to implement Markdown formatting yourself.
Offers a highly accurate Speech-to-Text API from a well-established transcription service, including features like speaker diarization and custom vocabulary.
Rev.ai provides a robust transcription API but, like other general-purpose services, doesn't include Spoken.md's specific podcast search capabilities. You would need to provide the audio source and handle the output formatting to Markdown.
More on Stork
Other tools in this category, matched by shared tags
One short daily email of tools worth shipping. No drip funnel.
one email a day · unsubscribe in two clicks · no third-party tracking
For builders
AI agents read it. Buyers land on it. It answers in eight languages and over MCP. Your tool can have one like it — live in 24 hours.
