Self-hosted audiobook studio

Settings

AI providers

Configured via server environment variables. API keys stay on the server.

None (manual transcript)
manual
Available
Local (llama.cpp / Ollama)
qwen3.5-9b
Available
OpenAI
gpt-4o-mini, gpt-4o, gpt-4.1-mini, gpt-4.1
Not configured
Anthropic (Claude)
claude-3-5-haiku-latest, claude-3-5-sonnet-latest, claude-sonnet-4-latest
Not configured
Google (Gemini)
gemini-2.0-flash, gemini-2.5-flash, gemini-2.5-pro, gemini-1.5-flash, gemini-1.5-pro
Available

TTS engines

Kokoro 1.0.0
28 voice(s): Heart (US F), Alloy (US F), Aoede (US F), Bella (US F), Jessica (US F), Kore (US F), Nicole (US F), Nova (US F), River (US F), Sarah (US F), Sky (US F), Adam (US M), Echo (US M), Eric (US M), Fenrir (US M), Liam (US M), Michael (US M), Onyx (US M), Puck (US M), Santa (US M), Alice (UK F), Emma (UK F), Isabella (UK F), Lily (UK F), Daniel (UK M), Fable (UK M), George (UK M), Lewis (UK M)
GPT-SoVITS v2
13 voice(s): Achernar, Aoede, Autonoe, Callirrhoe, Charon, Fenrir, Kore, Leda, Orus, Puck, Sadie, sadie-excited, Zephyr
F5-TTS v1
13 voice(s): Achernar, Aoede, Autonoe, Callirrhoe, Charon, Fenrir, Kore, Leda, Orus, Puck, Sadie, sadie-excited, Zephyr
Orpheus v1
8 voice(s): Tara, Leah, Jess, Leo, Dan, Mia, Zac, Zoe
Voxtral v6
20 voice(s): Casual Female, Casual Male, Cheerful Female, Neutral Female, Neutral Male, Fr Female, Fr Male, Es Female, Es Male, De Female, De Male, It Female, It Male, Pt Female, Pt Male, Nl Female, Nl Male, Ar Male, Hi Female, Hi Male
Omni v7:IndexTeam/IndexTTS-2:Vector:0.4:320
13 voice(s): Achernar, Aoede, Autonoe, Callirrhoe, Charon, Fenrir, Kore, Leda, Orus, Puck, Sadie, sadie-excited, Zephyr
Gemini v1
30 voice(s): Zephyr (Bright), Puck (Upbeat), Charon (Informative), Kore (Firm), Fenrir (Excitable), Leda (Youthful), Orus (Firm), Aoede (Breezy), Callirrhoe (Easy-going), Autonoe (Bright), Enceladus (Breathy), Iapetus (Clear), Umbriel (Easy-going), Algieba (Smooth), Despina (Smooth), Erinome (Clear), Algenib (Gravelly), Rasalgethi (Informative), Laomedeia (Upbeat), Achernar (Soft), Alnilam (Firm), Schedar (Even), Gacrux (Mature), Pulcherrima (Forward), Achird (Friendly), Zubenelgenubi (Casual), Vindemiatrix (Gentle), Sadachbia (Lively), Sadaltager (Knowledgeable), Sulafat (Warm)

Environment variables

  • OPENAI_API_KEY, OPENAI_MODEL, OPENAI_BASE_URL
  • ANTHROPIC_API_KEY, ANTHROPIC_MODEL, ANTHROPIC_BASE_URL
  • LLM_BASE_URL, LLM_MODEL, LLM_API_KEY (local llama.cpp / Ollama)
  • SOVITS_BASE_URL, SOVITS_VOICES, SOVITS_REF_AUDIO, SOVITS_REF_TEXT