Our rating: 3/5 for this setup

Self-hosted Otter alternative with Speakr: transcripts, speakers, search

A Docker app on a home server: upload a recording (or record in the browser) and it transcribes it, labels each speaker, and keeps audio and transcript together in a searchable archive. Optional AI summaries and a chat to ask questions about long transcripts.

New Added Oct 17, 2026 · ✓ Last checked Oct 17, 2026

It broke for meBroke?

Diagram drawn by AppToBot from this recipe's source. It shows the flow, not a screenshot of the product.

Setup steps

Install Speakr with Docker on your server
Choose transcription: self-hosted WhisperX or a provider API such as OpenAI's
Connect an LLM for summaries (local or cloud)
Upload a recording or record in the browser
Review the speaker-labelled transcript; click lines to replay the audio

Steps summarized from the original Blog source ↗. Use “Copy” to grab them with the tools and source link, or copy an AI prompt.

How it went

Since setting it up, the writer uses Speakr to transcribe all their calls and meetings. Speaker labels and a transcript synced to the audio make it quick to find and check who said what.

Worth knowing

Transcription quality dips a bit with local models. The built-in chat for querying transcripts didn't work perfectly for the writer, and they rarely use the AI summaries.

Only what the original source ↗ says, re-read Oct 17, 2026. How we write these

Try it with AI

Paste this into ChatGPT, Claude or your own agent for step-by-step help. Prompt written by AppToBot from this recipe's data, not by the original author. It keeps drafts for your review and asks before anything is sent or paid.

Help me set up this automation using Speakr (open source) + WhisperX or a cloud speech API + local LLM: "Self-hosted Otter alternative with Speakr: transcripts, speakers, search".
Goal: replace Otter.ai meeting transcription.

How it should work:
- Trigger: You upload a recording or record in the browser
- Then: Transcribes it automatically
- Then: Labels each speaker
- Then: Stores audio and transcript in a searchable archive
- Result: Speaker-labelled transcript you can search and replay

Setup steps (summarized from the original source):
1. Install Speakr with Docker on your server
2. Choose transcription: self-hosted WhisperX or a provider API such as OpenAI's
3. Connect an LLM for summaries (local or cloud)
4. Upload a recording or record in the browser
5. Review the speaker-labelled transcript; click lines to replay the audio

Guide me one step at a time. Ask me for anything you need (accounts, sheet or channel names) before you start.

Safety rules:
- Build and test with sample data first, and show me a sample result before anything goes live.
- Keep anything that goes to other people (emails, posts, replies, record updates) as drafts for my review until I say otherwise.
- Never send, post, buy, pay, delete or change records without my approval.
- Tell me about any cost (paid plans, API usage) before I'd incur it, and help me set a spending limit.
- Keep API keys and passwords out of shared docs and chats.
- Privacy: With self-hosted WhisperX and a local LLM, recordings stay on your server; with a provider API, audio goes to that provider.

Based on: https://www.xda-developers.com/ditched-otterai-for-app-that-transcribes-meeting-stores-searchable-place/

Otter.ai meeting transcriptionSpeakr (open source) + WhisperX or a cloud speech API + local LLM

Tool names link to each official site (opens in a new tab).

Cost afterFree with self-hosted models; cloud models 'cost barely any pennies' (per writer)

SetupMedium · Not reported

Time savedNot reported

SkillIntermediate

Running cost: Free to run Free open-source app; the writer runs a local LLM and says cloud models cost only pennies if you choose them. Self-hosted How we sort costs
Replace an app: AI bots that replace Otter

App vs bot, side by side

Old app vs bot
	Old app / habit	Bot
Tool	Otter.ai	Speakr on a home server + WhisperX (or a provider API) + a local LLM
Monthly cost	Not reported (the writer found Otter's free plan too limiting and didn't want to pay)	Free with self-hosted models; cloud models 'cost barely any pennies' (per writer)
Setup	None (already in use)	Not reported · Intermediate
Your time	Baseline	Not reported
Maintenance	Handled by vendor/you as before	Keep the Docker app and models updated; choose self-hosted WhisperX or a provider API.
Privacy	Data stays with the app vendor	With self-hosted WhisperX and a local LLM, recordings stay on your server; with a provider API, audio goes to that provider.

Full comparison

Replaces	Otter.ai
Bot / agent stack	Speakr on a home server + WhisperX (or a provider API) + a local LLM
Monthly cost before	Not reported (the writer found Otter's free plan too limiting and didn't want to pay)
Monthly cost after	Free with self-hosted models; cloud models 'cost barely any pennies' (per writer)
Setup time	Not reported
Time saved	Not reported
Skill level	Intermediate
Reliability	3/5: firsthand daily use but no usage period or error figures; the transcript is synced to the audio, so you can check any line.
Maintenance	Keep the Docker app and models updated; choose self-hosted WhisperX or a provider API.
Privacy & data	With self-hosted WhisperX and a local LLM, recordings stay on your server; with a provider API, audio goes to that provider.
Best for	People with a home server who record many calls and interviews
Not for	People who want a bot that joins meetings automatically

Pros and cons

Pros

Speaker labels in every transcript
Click a line to replay the audio and check it
One searchable archive of all recordings

Cons

Needs a home server and Docker
Local models transcribe a bit worse; the transcript chat didn't work perfectly for the writer

Source and evidence

First-person XDA Developers article (Aug 2026): since setting it up, the writer uses it for all their calls and meetings. Open-source project (AGPL-3.0, about 4.1k GitHub stars when we checked).

Read the original Blog source ↗

“Not reported” means the source doesn't say. We never fill gaps with guesses. Numbers marked “per author” or “vendor claim” are the source's own and weren't independently tested. Source last checked Oct 17, 2026.

Our rating is an editorial opinion based on the public source above, not lab testing. Spot an error? Request a correction.

Plain-text summary (for search and AI assistants)

Self-hosted Otter alternative with Speakr: transcripts, speakers, search. Replaces Otter.ai with Speakr on a home server + WhisperX (or a provider API) + a local LLM. Cost before: Not reported (the writer found Otter's free plan too limiting and didn't want to pay). Cost after: Free with self-hosted models; cloud models 'cost barely any pennies' (per writer). Setup: Not reported, Intermediate. Time saved: Not reported. Reliability 3/5: 3/5: firsthand daily use but no usage period or error figures; the transcript is synced to the audio, so you can check any line. Best for: People with a home server who record many calls and interviews. Not for: People who want a bot that joins meetings automatically. How it went (per source): Since setting it up, the writer uses Speakr to transcribe all their calls and meetings. Speaker labels and a transcript synced to the audio make it quick to find and check who said what. Worth knowing: Transcription quality dips a bit with local models. The built-in chat for querying transcripts didn't work perfectly for the writer, and they rarely use the AI summaries. Source: https://www.xda-developers.com/ditched-otterai-for-app-that-transcribes-meeting-stores-searchable-place/

Compare with another recipe ← All recipes

Questions, corrections or ideas?

Spotted an error, want a recipe covered, or have a partnership idea? Send us a message and we'll get back to you.

Starting your own newsletter? Try beehiiv ↗

What is beehiiv?

beehiiv is a newsletter platform: you write and send emails, host a newsletter website, and grow and monetize a list from one place. We've used it for our own newsletter.

beehiiv says (vendor claims, not tested by us):

Free plan with up to 2,500 subscribers and unlimited sends
Built-in website, recommendation network and analytics
0% cut of paid subscription revenue (Stripe fees apply)

Good for: starting or growing an email newsletter. Not ideal for: email automations or removing beehiiv branding on a $0 budget (those need Lite or Pro).

Free plan: $0, no card needed. Paid plans from $49/mo billed annually (Lite, up to 1,000 subscribers). People who sign up through our link get a 14-day trial plus 20% off their first 3 months, per beehiiv's partner page. Facts as of Oct 2026, from beehiiv's own website. More about beehiiv →