# panyanyany/Twocast

AI Podcast Generator for bilingual episodes, Multi Languages, Alternative to NotebookLLM；真人对话AI播客生成器，多语言，多音色

Repository: https://github.com/panyanyany/Twocast
Canonical: https://ross.abutalabs.com/products/twocast
Homepage: https://twocast.app/
Language: TypeScript
License Family: other
Topics: podcast, podcast-generator, voice-cloning, voice-synthesis
Last push: 2025-07-01T03:46:15+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 29, release rhythm 35, longevity 31
- inputs: {"age_days": 439, "days_push": 428, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1290, forks 130 (observed 2026-08-28T04:04:15.409055+00:00)

## What it is
Twocast is a self-hostable AI podcast generator that creates two-person conversational podcast episodes from topics, links, documents, or web pages, with multi-language and multi-voice support. It integrates TTS providers (Fish Audio, Minimax, Google Gemini) and an LLM (via OpenRouter) to produce audio, outline, and script, with a hosted version offering paid credits.

## Use cases
- generate a two-person ai podcast from a url or pdf
- notebooklm alternative for podcast generation
- create bilingual podcast episodes with ai voices
- turn hacker news or blog posts into a podcast
- self-host an ai podcast generator with my own tts api keys
- convert documents into a conversational audio show

## When to choose
- you want multi-host conversational podcasts generated from links, docs, or topics
- you need multi-language or bilingual episodes with distinct voices
- you prefer self-hosting with your own Fish Audio, Minimax, or Gemini keys

## When to avoid
- you need single-narrator text-to-speech or fine-grained audio editing rather than generated dialogue
- you want a fully free offline solution - it depends on paid third-party TTS and LLM APIs
- you need a permissively licensed project - the repo currently has no license

## Facets
- artifact type: application
- maturity: active
- function: tts, llm-inference, audio-processing, web-framework, rag
- domain: artificial-intelligence, large-language-models, media, self-hosted
- platform: self-hosted, cross-platform
- tags: podcast-generator, text-to-speech, two-person-dialogue, notebooklm-alternative, voice-synthesis, bilingual, fish-audio, minimax, gemini, audio, natural-language-processing, nodejs, docker, web-server

## Member repositories
- panyanyany/Twocast (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:15.409055+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:55:40.433558+00:00, confidence not recorded.
  - readme: https://github.com/panyanyany/Twocast (fetched 2026-08-28T04:04:15.409055+00:00, sha 740c3e66631a)
  - homepage: https://twocast.app/ (fetched 2026-08-29T12:11:51.043555+00:00, sha 8200eedbcca7)
  - site_page: https://twocast.app/pricing (fetched 2026-08-29T12:11:51.046316+00:00, sha 4e20a453307b)
- Data as of 2026-08-30T08:39:29.467469+00:00.