Tags déi d'gewielt Modell verstinn - klickt fir eng an Ärem Text ze setzen wou se geschitt:
Dëse Modell liest einfache Text, sou datt Inline-Tags ignoréiert ginn. Fir Tag-baséiert Emotiounen, wielt e expressiven Modell wéi Orpheus oder Bark.
Natierlech Sprooch Lieferung Cues. Honoréiert vun Qwen3-TTS haut; aner expressiv Modeller kommen bald.
D'Modell ass net méi verfügbar, et gëtt awer nach ëmmer e puer Modeller (z. B. den 3000).
Piper was built by the Rhasspy project to bring neural text-to-speech to edge devices that have no GPU. It pairs a VITS-style synthesizer with the Larynx pipeline and runs as a compact ~15M-parameter ONNX model directly on CPU, so synthesis happens locally with no cloud round-trip. Its strength is breadth and footprint: over 100 voices spanning 35+ languages at real-time speed on hardware as modest as a Pi 4. That makes it the practical default for home automation, accessibility readers, and offline kiosks where latency, privacy, and zero hosting cost matter more than studio polish.
Bescht fir: Quick previews, accessibility, and embedded applications
FräiFemaleFir perséinlech a net-kommerziell Notzung
Aivars (Latvian)
Latvian
FräiMale
Alan (UK)
English
FräiMaleFir perséinlech a net-kommerziell Notzung
Alba (UK)
English
FräiFemaleFir perséinlech a net-kommerziell Notzung
Amir (Persian)
fa
FräiMaleFir perséinlech a net-kommerziell Notzung
Amy (US)
English
FräiFemaleFir perséinlech a net-kommerziell Notzung
Anna (Hungarian)
Hungarian
FräiFemaleFir perséinlech a net-kommerziell Notzung
Antton (Basque)
Basque
FräiMaleFir perséinlech a net-kommerziell Notzung
Artur (Slovenian)
Slovenian
FräiMale
Berfin (Kurdish)
Kurdish
FräiFemaleFir perséinlech a net-kommerziell Notzung
DFKI (Turkish)
Turkish
FräiNeutralFir perséinlech a net-kommerziell Notzung
Darkman (Polish)
Polish
FräiMaleFir perséinlech a net-kommerziell Notzung
Denis (Russian)
Russian
FräiMaleFir perséinlech a net-kommerziell Notzung
Dutch (MLS)
Dutch
FräiNeutral
Edon (Albanian)
Albanian
FräiMaleFir perséinlech a net-kommerziell Notzung
Eva (German)
German
FräiFemale
Faber (Portuguese)
Portuguese
FräiMaleFir perséinlech a net-kommerziell Notzung
Fasih (Urdu)
Urdu
FräiMaleFir perséinlech a net-kommerziell Notzung
Google (Nepali)
Nepali
FräiNeutralFir perséinlech a net-kommerziell Notzung
Gor (Armenian)
hy
FräiMale
Gwryw (Welsh)
cy
FräiMaleFir perséinlech a net-kommerziell Notzung
Harri (Finnish)
Finnish
FräiMaleFir perséinlech a net-kommerziell Notzung
Huayan (Chinese)
Chinese
FräiFemaleFir perséinlech a net-kommerziell Notzung
Issai (Kazakh)
Kazakh
FräiNeutral
Jenny (UK)
English
FräiFemaleFir perséinlech a net-kommerziell Notzung
Jirka (Czech)
Czech
FräiMaleFir perséinlech a net-kommerziell Notzung
Joe (US)
English
FräiMaleFir perséinlech a net-kommerziell Notzung
Kareem (Arabic)
Arabic
FräiMaleFir perséinlech a net-kommerziell Notzung
Lada (Ukrainian)
Ukrainian
FräiFemale
Lanfrica (Swahili)
Swahili
FräiNeutralFir perséinlech a net-kommerziell Notzung
Lessac (US)
English
FräiMaleFir perséinlech a net-kommerziell Notzung
Lili (Slovak)
Slovak
FräiFemaleFir perséinlech a net-kommerziell Notzung
Maider (Basque)
Basque
FräiFemaleFir perséinlech a net-kommerziell Notzung
Marylux (Luxembourgish)
lb
FräiFemaleFir perséinlech a net-kommerziell Notzung
Mihai (Romanian)
Romanian
FräiMaleFir perséinlech a net-kommerziell Notzung
NST (Swedish)
Swedish
FräiNeutral
Natia (Georgian)
Georgian
FräiFemaleFir perséinlech a net-kommerziell Notzung
News (Indonesian)
Indonesian
FräiNeutralFir perséinlech a net-kommerziell Notzung
Ona (Catalan)
ca
FräiFemaleFir perséinlech a net-kommerziell Notzung
Rapunzelina (Greek)
Greek
FräiFemaleFir perséinlech a net-kommerziell Notzung
Rdh (Dutch, Flemish)
Dutch
FräiMale
Riccardo (Italian)
Italian
FräiMale
Ryan (US)
English
FräiMaleFir perséinlech a net-kommerziell Notzung
Salka (Icelandic)
Icelandic
FräiFemale
Serbian Institute
Serbian
FräiNeutralFir perséinlech a net-kommerziell Notzung
Sharvard (Spanish)
Spanish
FräiMaleFir perséinlech a net-kommerziell Notzung
Siwis (French)
French
FräiFemaleFir perséinlech a net-kommerziell Notzung
Tale (Danish)
Danish
FräiNeutralFir perséinlech a net-kommerziell Notzung
Tale (Norwegian)
Norwegian
FräiNeutralFir perséinlech a net-kommerziell Notzung
Thorsten (German)
German
FräiMaleFir perséinlech a net-kommerziell Notzung
VIVOS (Vietnamese)
Vietnamese
FräiNeutralFir perséinlech a net-kommerziell Notzung
Piper Lëscht vun de FAQ
No. Piper is CPU-only by design and uses 0 VRAM — it runs offline on embedded hardware like a Raspberry Pi 4 in real time, which is exactly what it was built for.
Only some voices. The Piper engine is MIT licensed, but each voice carries the license of the recordings it was trained on, and most Piper voices were trained on or fine-tuned from recordings licensed for non-commercial use. Those voices are marked "Personal and non-commercial use only" below and in the voice picker. On TTS.ai, audio from the other Piper voices is for personal use on the free tier and can be used commercially on any paid plan.
Piper offers 100+ voices across 35+ languages, including English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian, Chinese, Arabic, Turkish, Ukrainian and many more. It supports SSML and handles up to 2,000 characters per request.