Tag kang dipahami model kang dipilih — klik kanggo ngethok siji menyang teks sampeyan ing ngendi iku kedadeyan:
Model ieu maca teks biasa, jadi tag inline diabaikan. Pikeun emosi dumasar tag, ganti ka model ekspresif kayaning Orpheus atawa Bark.
Cues pangiriman basa alami. Dihormat ku Qwen3-TTS ayeuna; model ekspresif séjénna bakal datang.
Model ieu henteu ngadukung instruksi gaya — ganti kana model anu ngadukung (contona Qwen3-TTS).
Nyathet pangucapan standar (kata = pangucapan):
-12
+12
Ngontrol ekspresifitas (0 = netral, 1 = banget ekspresif)
Beban panuntun tanpa klasifikator (luwih dhuwur = luwih nuntun)
Nyathet gaya swara nganggo basa alami (Parler nggunakake iki tinimbang swara sing ditetepake)
Формат диалога: Gunake tag [S1] lan [S2] kanggo nyambungake pamicara sing beda. Conto: [S1] Halo! [S2] Halo, apa kabarmu?
OuteTTS by OuteAI takes a language-model approach to speech: it extends an LLM with text-to-speech capability while keeping the original architecture intact, so it can run through standard LLM tooling. That gives it unusually broad backend support — llama.cpp on CPU or GPU, Hugging Face Transformers, ExLlamaV2, VLLM, and even in-browser inference via Transformers.js. It is a natural fit for edge deployment and low-resource environments where running a model client-side or on CPU matters more than raw speed. On TTS.ai it is offered on the free tier for English. Because the LLM-based pipeline is slow on long inputs, it is best used for shorter regular text rather than long-form cloning.
Paling apik kanggo: Edge deployment, browser-based TTS, low-resource environments
CC BY-NC-SA 4.0 (weights, non-commercial) + Llama 3.2 Community (base)
Mung kanggo panggunaan pribadi lan ora komersial
Tingkat
free
Kecepatan
slow
Kloning suara
Ora
Basa
English
Karakter paling akeh
1000
OuteTTS suara
Female 1 (Neutral)
English
BebasFemaleMung kanggo panggunaan pribadi lan ora komersial
OuteTTS TTS — FAQ
Across many backends — llama.cpp (CPU or GPU), Hugging Face Transformers, ExLlamaV2, VLLM, and even directly in the browser through Transformers.js — because it preserves the underlying LLM architecture.
Its LLM-based design runs efficiently on CPU and in the browser, so it can operate client-side or on modest hardware without a dedicated GPU.
It works best on shorter inputs. The LLM-based pipeline is slow on long passages, so it is offered for regular short-to-medium TTS rather than long-form generation.
Ngetik alamat surélék anjeun pikeun terus ngahasilkeun basa gratis, atanapi ngadaptar pikeun 15.000 karakter bonus.
Ora perlu tembung sandhi — kita bakal ngirim link kanggo ngganti tembung sandhi mengko.
Ambang Lapisan Bebas Dicapai
Anjeun geus dipaké 5,000 karakter bébas poéan anjeun. Nyiptakeun akun bébas pikeun meunangkeun 15,000 karakter bonus plus 10,000 karakter bébas unggal bulan.
