Piper

Piper 음성 인식

A fast, CPU-only neural TTS engine from Rhasspy that runs entirely offline, even on a Raspberry Pi.

가입하기 5,000자 한도

정확한 제어를 위해 SSML 태그로 텍스트를 래핑하십시오.

<speak><prosody rate="slow">Slow speech</prosody></speak>

선택한 모델이 이해하는 태그 — 텍스트에 드래그하려면 클릭하세요:

이 모델은 일반 텍스트를 읽기 때문에 인라인 태그는 무시됩니다. 태그 기반 감정을 위해서는 Orpheus 또는 Bark과 같은 표현 모델로 전환하십시오.

사용자 지정 발음 정의 (단어 = 발음):

-12 +12
0.5x 2.0x
파이퍼, VITS, MeloTTS와 무료
생성된 오디오가 여기에 나타납니다. 모델을 선택하고 텍스트를 입력한 다음 생성 을 클릭합니다.
오디오가 성공적으로 생성되었습니다
0:00
오디오 다운로드 .srt 파일 다운로드 링크는 24시간 이내에 만료됩니다.
무료 계층: 개인용. 상업용 라이센스 최저 $5/mo
이것을 당신의 목소리로 만들어라 30초만에 목소리 복제
TTS.ai가 마음에 드시나요? 친구들에게 알려주세요!

정보 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.

최적화된 용도: Quick previews, accessibility, and embedded applications

모두 찾아보기 Piper 목소리

한눈에

개발자
Rhasspy
라이선스
MIT
free
속도
fast
음성 복제
아니요
언어
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
최대 문자수
2000

Piper 목소리

Aivars (Latvian)

Latvian
자유 Male

Alan (UK)

English
자유 Male

Alba (UK)

English
자유 Female

Amir (Persian)

fa
자유 Male

Amy (US)

English
자유 Female

Anna (Hungarian)

Hungarian
자유 Female

Artur (Slovenian)

Slovenian
자유 Male

DFKI (Turkish)

Turkish
자유 Neutral

Darkman (Polish)

Polish
자유 Male

Denis (Russian)

Russian
자유 Male

Dutch (MLS)

Dutch
자유 Neutral

Faber (Portuguese)

Portuguese
자유 Male

Google (Nepali)

Nepali
자유 Neutral

Gwryw (Welsh)

cy
자유 Male

Harri (Finnish)

Finnish
자유 Male

Huayan (Chinese)

Chinese
자유 Female

Issai (Kazakh)

Kazakh
자유 Neutral

Jenny (UK)

English
자유 Female

Jirka (Czech)

Czech
자유 Male

Joe (US)

English
자유 Male

Kareem (Arabic)

Arabic
자유 Male

Lada (Ukrainian)

Ukrainian
자유 Female

Lanfrica (Swahili)

Swahili
자유 Neutral

Lessac (US)

English
자유 Male

Lili (Slovak)

Slovak
자유 Female

Marylux (Luxembourgish)

lb
자유 Female

Mihai (Romanian)

Romanian
자유 Male

NST (Swedish)

Swedish
자유 Neutral

Natia (Georgian)

Georgian
자유 Female

Ona (Catalan)

ca
자유 Female

Rapunzelina (Greek)

Greek
자유 Female

Riccardo (Italian)

Italian
자유 Male

Ryan (US)

English
자유 Male

Salka (Icelandic)

Icelandic
자유 Female

Serbian Institute

Serbian
자유 Neutral

Sharvard (Spanish)

Spanish
자유 Male

Siwis (French)

French
자유 Female

Tale (Danish)

Danish
자유 Neutral

Tale (Norwegian)

Norwegian
자유 Neutral

Thorsten (German)

German
자유 Male

VIVOS (Vietnamese)

Vietnamese
자유 Neutral

Piper TTS — 자주 묻는 질문

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.

Yes. Piper is released under the MIT license, so it is free to use in commercial and personal projects.

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.
← 모든 음성