TranscriptFetch's answer

It started with discovering there is no good way to get the text of a video. YouTube’s official Data API will confirm a caption track exists and then refuse to hand it over, because captions.download requires the video owner’s OAuth token. The popular open-source libraries work until you deploy them, at which point platforms start refusing datacenter IPs. And YouTube is the easy case: TikTok and Instagram publish no caption file at all. Every workaround solved one platform, worked locally, and broke in production. TranscriptFetch is the version that handles the failure cases as first-class behaviour rather than edge cases.

Donkey.support's answer:

Donkey.support was created out of a need for a streamlined and integrated customer support solution, particularly for independent founders and small teams. The founder, sjorsfest, experienced the friction of context switching between various work tools and support platforms. Donkey.support was developed to solve this by allowing support to be managed directly from the communication tools teams already use, like Slack and Discord, with an easy-to-implement chat widget for websites. The goal is to provide an effective, affordable, and no-bloat support system for indie makers and startups.

TranscriptFetch's answer

Developers and technical teams building on video and web content. The common cases are RAG and retrieval pipelines that need video as text, AI agents that need to read a link mid-conversation, content teams repurposing short-form video at scale, and media monitoring and research tools. It is an API first, so the buyer is usually the person writing the integration rather than an end user. The free browser tools exist for one-off transcripts and for evaluating output quality before writing any code.

Donkey.support's answer:

The primary audience for Donkey.support consists of indie founders, solo founders, and small startup teams who are actively involved in their company's support operations. This includes developers building SaaS products and bootstrapped businesses that require an efficient, no-frills customer support solution. The ideal user values simplicity, affordability, and the ability to manage support from within their existing communication channels like Slack or Discord.

TranscriptFetch's answer

Most short-form video has no caption track to download. TikTok’s auto-captions are opt-in per upload, Instagram never publishes a downloadable track, and many captions on both are burned into the video frames where no parser can read them. TranscriptFetch transcribes the audio when no caption track exists, on the same endpoint, with the same response shape. Your code never branches on which method produced the text. It also covers YouTube, TikTok, Instagram, X and Facebook plus any web page as clean Markdown, so a pipeline spanning several sources is one integration rather than five.

Donkey.support's answer:

Donkey.support stands out due to its unique positioning as a support chat widget that lives directly within your Discord server. It offers the flexibility to reply from Slack, Discord, or Telegram, eliminating the need for context switching. Key differentiators include unique features like automatic email follow-ups for missed replies, customizable widgets, and verified visitor context through signed metadata. It's designed for simplicity, allowing for a live setup in minutes, with pricing structured for indie founders, avoiding per-seat costs. The emphasis on being a simple, effective tool without bloat also sets it apart.

Donkey.support's answer:

As Donkey.support is targeted towards indie founders and small startups, it does not have a list of "biggest customers" in the traditional enterprise sense. Its user base consists of numerous small businesses and independent creators who are looking for an efficient and affordable customer support solution.

TranscriptFetch's answer

Three reasons. Coverage: one API key and one response shape across five video platforms and the open web, instead of stitching together a library per platform. Reliability: requests run through rotating infrastructure, so code that works locally keeps working from a server, which is where most open-source approaches break. Billing that matches reality: one credit per successful response, with failed, blocked and empty results never charged. That last point matters on short-form video, where a meaningful share of any batch is music with no speech in it. There is also an MCP server, so AI agents can fetch transcripts as a tool without a custom integration.

Donkey.support's answer:

Donkey.support offers a unique blend of convenience, affordability, and integration. Unlike competitors that may require complex setup or have expensive per-seat pricing, Donkey.support allows for a live setup in minutes and is priced with indie founders in mind. Its core strength lies in allowing support replies directly from platforms teams already use, such as Slack, Discord, or Telegram, thus minimizing context switching. The features like automatic email follow-ups and customizable widgets provide a comprehensive yet uncomplicated support solution, making it an attractive choice for small, agile teams.

TranscriptFetch's answer

Next.js with TypeScript and Tailwind on the front end and API layer, Clerk for auth with SHA-256 hashed API keys, Neon Postgres with Drizzle ORM, Redis for caching, and Stripe for billing. The extraction layer is a Python and FastAPI service. Speech-to-text uses Whisper-class models. The MCP server is published in the official Model Context Protocol registry with a DNS-verified namespace.

Donkey.support's answer:

Donkey.support is built using a modern web stack, including a robust backend and a flexible frontend. The core technologies leverage cloud infrastructure for scalability and reliability. Specific details on the exact programming languages and frameworks are not publicly disclosed, but the focus is on a smooth and efficient user experience.