Piper Mga TNT
A fast, CPU-only neural TTS engine from Rhasspy that runs entirely offline, even on a Raspberry Pi.
Mag-sign up para sa 5,000 character na limitasyon
I-wrap ang iyong teksto sa SSML tags para sa tumpak na kontrol:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tags ang napili modelo nauunawaan — i-click upang ihulog ang isa sa iyong teksto kung saan ito ay nangyayari:
Ang modelong ito ay nagbabasa ng karaniwang teksto, kaya inline tags ay hindi pinapansin. Para sa tag-based na damdamin, lumipat sa isang makahulugang modelo tulad ng Orpheus o Bark.
Tukuyin ang mga pasadyang mga panlapi (word = panlapi):
-12
+12
0.5x
2.0x
Libreng may Piper, VITS, MeloTTS
Ang iyong ginawang audio ay lilitaw dito. Pumili ng modelo, ipasok ang teksto, at i-click ang Bumuo.
Pagbuo ay nabigo
Audio nabuo Matagumpay
Free tier: personal na paggamit. Komersyal na lisensya mula sa $5/buwan
Patakbo mababa sa libreng mga character
Kumuha ng 200K character bawat buwan — $5/mo
o isang isang beses na 100K pack para sa $5
Gumawa ito ng iyong sariling boses
Clone ng isang boses sa 30 segundo
Tungkol sa Piper
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.
Pinakamahusay para sa: Quick previews, accessibility, and embedded applications
Mag-browse ng lahat Piper Mga bosesSa isang sulyap
- Developer
- Rhasspy
- Lisensya
- MIT (engine); voice licenses vary
- Mga hayop
- free
- Bilis
- fast
- Pag-clone ng boses
- Hindi
- Wika
- English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian, Chinese, Arabic, Czech, Danish, Finnish, Greek, Hungarian, Icelandic, Georgian, Kazakh, Nepali, Norwegian, Romanian, Slovak, Serbian, Swedish, Swahili, Turkish, Ukrainian, Vietnamese, CA, CY, FA, Latvian, Slovenian, LB, Basque, Indonesian, Kurdish, Malayalam, Albanian, Telugu, Urdu
- Max character
- 2000
Piper Mga boses
Aegis (Urdu)
Urdu
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Aivars (Latvian)
Latvian
Libre
Male
Alan (UK)
English
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Alba (UK)
English
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Amir (Persian)
fa
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Amy (US)
English
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Anna (Hungarian)
Hungarian
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Antton (Basque)
Basque
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Artur (Slovenian)
Slovenian
Libre
Male
Berfin (Kurdish)
Kurdish
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
DFKI (Turkish)
Turkish
Libre
Neutral
Personal at hindi pang-komersyal na paggamit lamang
Darkman (Polish)
Polish
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Denis (Russian)
Russian
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Dutch (MLS)
Dutch
Libre
Neutral
Edon (Albanian)
Albanian
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Faber (Portuguese)
Portuguese
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Fasih (Urdu)
Urdu
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Google (Nepali)
Nepali
Libre
Neutral
Personal at hindi pang-komersyal na paggamit lamang
Gor (Armenian)
hy
Libre
Male
Gwryw (Welsh)
cy
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Harri (Finnish)
Finnish
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Huayan (Chinese)
Chinese
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Issai (Kazakh)
Kazakh
Libre
Neutral
Jenny (UK)
English
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Jirka (Czech)
Czech
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Joe (US)
English
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Kareem (Arabic)
Arabic
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Lada (Ukrainian)
Ukrainian
Libre
Female
Lanfrica (Swahili)
Swahili
Libre
Neutral
Personal at hindi pang-komersyal na paggamit lamang
Lessac (US)
English
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Lili (Slovak)
Slovak
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Maider (Basque)
Basque
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Marylux (Luxembourgish)
lb
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Mihai (Romanian)
Romanian
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
NST (Swedish)
Swedish
Libre
Neutral
Natia (Georgian)
Georgian
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
News (Indonesian)
Indonesian
Libre
Neutral
Personal at hindi pang-komersyal na paggamit lamang
Ona (Catalan)
ca
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Rapunzelina (Greek)
Greek
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Riccardo (Italian)
Italian
Libre
Male
Ryan (US)
English
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Salka (Icelandic)
Icelandic
Libre
Female
Serbian Institute
Serbian
Libre
Neutral
Personal at hindi pang-komersyal na paggamit lamang
Sharvard (Spanish)
Spanish
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
Siwis (French)
French
Libre
Female
Personal at hindi pang-komersyal na paggamit lamang
Tale (Danish)
Danish
Libre
Neutral
Personal at hindi pang-komersyal na paggamit lamang
Tale (Norwegian)
Norwegian
Libre
Neutral
Personal at hindi pang-komersyal na paggamit lamang
Thorsten (German)
German
Libre
Male
Personal at hindi pang-komersyal na paggamit lamang
VIVOS (Vietnamese)
Vietnamese
Libre
Neutral
Personal at hindi pang-komersyal na paggamit lamang
Piper Mga katanungan at sagot
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.