EVERYTHING XIAOMI
Get listed

Podlog

Podlog is a free, open-source, self-hosted web app for transcribing audio, searching transcripts, and analyzing podcast metadata.

Place
#21 of 25
Score
5.8
Podlog's website

What Podlog is

Podlog is a free, open-source, self-hosted web app for transcribing audio, searching transcripts, and analyzing podcast metadata. It can ingest episodes from RSS feeds or take audio uploads through its web interface. WhisperX handles transcription, and local pyannote diarization labels speakers; users can rename or merge those labels in the UI. An optional paid pyannote.ai cloud model is another diarization choice. Hybrid search combines full-text keywords with pgvector semantic similarity. Ask AI provides streamed, citation-backed answers from the transcript library, using local Ollama by default or optional Fireworks inference. Users can play audio from transcript timestamps and export transcripts or search results as Markdown or plain text. The Meta-Analysis dashboard summarizes speaker minutes, word counts, and host-versus-guest talking time across feeds. Podlog supports Telegram and email alerts, plus an optional Telegram bot for searching, questions, transcripts, queue checks, and adding sources. The project describes its default setup as local-first, with no accounts, cloud, or telemetry. Setup requires Docker Compose V2 and a Hugging Face access token; diarization also requires accepting the pyannote model license. Published container images support linux/amd64; other architectures require building from source.

Good

  • Ingests audio from RSS feeds or file uploads.
  • Combines keyword and semantic transcript search.
  • Ask AI answers with citations from the transcript library.
  • Exports transcripts and search results as Markdown or plain text.
  • Local-first by default, without accounts or telemetry.

Watch out

  • Requires Docker Compose V2 and a Hugging Face access token.
  • Diarization requires accepting the pyannote model license.
  • Published container images support linux/amd64 only.
  • Processing is CPU-only and sequential.

Who it suits

Podlog suits people who want to run podcast transcription and transcript search on their own server. It is best suited to users able to meet its documented deployment and hardware requirements.

Verdict

Podlog combines transcription, transcript search, and podcast metadata analysis in a self-hosted package. Its setup requirements and architecture support should be checked before deployment.

The facts

Each one read from Podlog's own pages, with the date it was checked.

What it does

Analytics
The Meta-Analysis dashboard reports speaker minutes, word counts, and host-versus-guest talking-time differences across feeds.checked 4 Oct 2026
Ask AI
Ask AI provides streamed, citation-backed answers from the transcript library, using local Ollama by default or optional Fireworks inference.checked 9 Oct 2026
Audio input
It can ingest episodes from RSS feeds or accept audio uploads, including MP3, M4A, WAV, OGG, FLAC, OPUS, AAC, WMA, WEBM, and MP4 files.checked 9 Oct 2026
Deployment limits
Published images support linux/amd64 only; other architectures require building from source.checked 9 Oct 2026
Deployment requirements
Installation requires Docker Compose V2 and a Hugging Face access token; users must accept the pyannote model license for diarization.checked 4 Oct 2026
Exports
Users can download search results or transcripts as Markdown or plain text, or use a print-friendly view.checked 9 Oct 2026
Exports and playback
Users can play audio from transcript timestamps and export transcripts or search results as Markdown or plain text.checked 4 Oct 2026
Hardware limits
The hardware guide lists 4-core x86-64 and 8 GB RAM as minimums, says GPU is not required, and notes processing is CPU-only and sequential.checked 4 Oct 2026
Integrations
Podlog supports Telegram and email notifications and an optional Telegram bot for search, questions, transcripts, queue checks, and adding sources.checked 4 Oct 2026
License
Podlog uses the O'Saasy License, which permits use and distribution but bars offering the software as a hosted service that directly competes with the licensor.checked 9 Oct 2026
Local model storage
The README says pulling all three local Ask AI models takes about 12 GB, and the first run downloads about 3 GB of Whisper and pyannote model weights.checked 9 Oct 2026
Notifications
Podlog supports Telegram and email alerts for episode completion or failure, with optional daily or weekly digests.checked 9 Oct 2026
Privacy
The project describes itself as local-first, with no accounts, cloud, or telemetry, while offering optional Fireworks remote inference.checked 9 Oct 2026
Purpose
Podlog is a self-hosted web app for audio transcription, search, and metadata analysis.checked 9 Oct 2026
Requirements
The documented prerequisites include Docker with Compose V2, a free Hugging Face account and access token, and accepting the pyannote model license for diarization.checked 9 Oct 2026
Search
Hybrid search combines full-text keyword search with pgvector semantic similarity.checked 9 Oct 2026
Speaker labels
Local pyannote diarization assigns speaker labels, and the UI lets users rename or merge speakers.checked 9 Oct 2026
Telegram bot
The optional Telegram bot can search, ask questions, fetch transcripts, check the queue, and add sources; it responds only to accounts on the configured allowlist.checked 9 Oct 2026
Transcription
Speech-to-text uses WhisperX with large-v3-turbo by default, configurable down to tiny for low-RAM machines.checked 9 Oct 2026
Transcription and speakers
It uses WhisperX for transcription and supports local speaker diarization, with an optional paid pyannote.ai cloud model.checked 4 Oct 2026

The company

Maker
The repository credits the project to @brlauuu; the linked GitHub profile identifies the maker as Đorđe.checked 9 Oct 2026

Where it runs

Platform constraint
Published container images support linux/amd64; other architectures require building from source.checked 4 Oct 2026

Alternatives to Podlog

All alternatives
  1. 1

    Rev

    Free planAndroidiOSWebAPI
    8.1From $25.49 a month
  2. 2Speechmatics logo

    Speechmatics

    Free planWebAPILinuxmacOS
    7.9From $0.01 a month
  3. 3AudioPod AI logo

    AudioPod AI

    Free planiOSWebAPI
    7.8From $20 a month
  4. 4Happy Scribe logo

    Happy Scribe

    Free planAndroidiOSAPImacOS
    7.8From $8.50 a month
  5. 5

    Simon Says

    Free planiOSWebExtensionmacOS
    7.7From $15 a month
  6. 6ElevenLabs logo

    ElevenLabs

    Free planWebAPI
    7.6From $6 a month