Piper TTS
A fast, CPU-only neural TTS engine from Rhasspy that runs entirely offline, even on a Raspberry Pi.
Wrap your text in SSML tags for precise control:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tags the selected model understands — click to drop one into your text where it happens:
This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.
Define custom pronunciations (word = pronunciation):
-12
+12
0.5x
2.0x
Free with Piper, VITS, MeloTTS
Your generated audio will appear here. Choose a model, enter text, and click Generate.
Generation Failed
Audio Generated Successfully
Free tier: personal use. Commercial license from $5/mo
Running low on free characters
Get 200K characters every month — $5/mo
or a one-time 100K pack for $5
Make this your own voice
Clone a voice in 30 seconds
About 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.
Best for: Quick previews, accessibility, and embedded applications
Browse all Piper voicesAt a glance
- Developer
- Rhasspy
- License
- MIT (engine); voice licenses vary
- Tier
- free
- Speed
- fast
- Voice cloning
- No
- Languages
- 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 characters
- 2000
Piper voices
Aegis (Urdu)
Urdu
Free
Female
Personal and non-commercial use only
Aivars (Latvian)
Latvian
Free
Male
Alan (UK)
English
Free
Male
Personal and non-commercial use only
Alba (UK)
English
Free
Female
Personal and non-commercial use only
Amir (Persian)
fa
Free
Male
Personal and non-commercial use only
Amy (US)
English
Free
Female
Personal and non-commercial use only
Anna (Hungarian)
Hungarian
Free
Female
Personal and non-commercial use only
Antton (Basque)
Basque
Free
Male
Personal and non-commercial use only
Artur (Slovenian)
Slovenian
Free
Male
Berfin (Kurdish)
Kurdish
Free
Female
Personal and non-commercial use only
DFKI (Turkish)
Turkish
Free
Neutral
Personal and non-commercial use only
Darkman (Polish)
Polish
Free
Male
Personal and non-commercial use only
Denis (Russian)
Russian
Free
Male
Personal and non-commercial use only
Dutch (MLS)
Dutch
Free
Neutral
Edon (Albanian)
Albanian
Free
Male
Personal and non-commercial use only
Faber (Portuguese)
Portuguese
Free
Male
Personal and non-commercial use only
Fasih (Urdu)
Urdu
Free
Male
Personal and non-commercial use only
Google (Nepali)
Nepali
Free
Neutral
Personal and non-commercial use only
Gor (Armenian)
hy
Free
Male
Gwryw (Welsh)
cy
Free
Male
Personal and non-commercial use only
Harri (Finnish)
Finnish
Free
Male
Personal and non-commercial use only
Huayan (Chinese)
Chinese
Free
Female
Personal and non-commercial use only
Issai (Kazakh)
Kazakh
Free
Neutral
Jenny (UK)
English
Free
Female
Personal and non-commercial use only
Jirka (Czech)
Czech
Free
Male
Personal and non-commercial use only
Joe (US)
English
Free
Male
Personal and non-commercial use only
Kareem (Arabic)
Arabic
Free
Male
Personal and non-commercial use only
Lada (Ukrainian)
Ukrainian
Free
Female
Lanfrica (Swahili)
Swahili
Free
Neutral
Personal and non-commercial use only
Lessac (US)
English
Free
Male
Personal and non-commercial use only
Lili (Slovak)
Slovak
Free
Female
Personal and non-commercial use only
Maider (Basque)
Basque
Free
Female
Personal and non-commercial use only
Marylux (Luxembourgish)
lb
Free
Female
Personal and non-commercial use only
Mihai (Romanian)
Romanian
Free
Male
Personal and non-commercial use only
NST (Swedish)
Swedish
Free
Neutral
Natia (Georgian)
Georgian
Free
Female
Personal and non-commercial use only
News (Indonesian)
Indonesian
Free
Neutral
Personal and non-commercial use only
Ona (Catalan)
ca
Free
Female
Personal and non-commercial use only
Rapunzelina (Greek)
Greek
Free
Female
Personal and non-commercial use only
Riccardo (Italian)
Italian
Free
Male
Ryan (US)
English
Free
Male
Personal and non-commercial use only
Salka (Icelandic)
Icelandic
Free
Female
Serbian Institute
Serbian
Free
Neutral
Personal and non-commercial use only
Sharvard (Spanish)
Spanish
Free
Male
Personal and non-commercial use only
Siwis (French)
French
Free
Female
Personal and non-commercial use only
Tale (Danish)
Danish
Free
Neutral
Personal and non-commercial use only
Tale (Norwegian)
Norwegian
Free
Neutral
Personal and non-commercial use only
Thorsten (German)
German
Free
Male
Personal and non-commercial use only
VIVOS (Vietnamese)
Vietnamese
Free
Neutral
Personal and non-commercial use only
Piper TTS — 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.