Umwandiko Kuri Abagenzuzi Indirimbo Kuri Umwandiko Guca umurongo Igishushanyo mbonera Ibiro Birenzeho
/

Gufungura Umwandiko Kuri

Every TTS model on our platform is open source, and most use MIT or Apache 2.0. A few models and voices are licensed for non-commercial use only and are marked 'Personal and non-commercial use only'. Use them through our hosted API, or self-host them on your own infrastructure with full control.

Gufungura Inkomoko Ifishi 2.0 Ibiro GitHub
Muhinduzi Inyandiko

Kugerageza

0/500
Na:,,,
Audio Kugaragara
Byaremwe
0:00
Iyimura
TTS.ai? Abayobozi!
Muhinduzi

Gufungura Inkomoko

Gufungura - Inkomoko kugirango

Gufungura Inkomoko

Every model on TTS.ai is open source, and each model page lists its license. No proprietary black boxes and no vendor lock-in.

Gufungura Inkomoko

Most models are licensed under MIT or Apache 2.0. A few use other licenses, and models or voices licensed for non-commercial use are marked "Personal and non-commercial use only".

Ibiro

Icyo ari cyo cyose Urugero na Gukoresha ku Amapareye. Igenzura KURI Ibyatanzwe,, na. Ikirere Bya ngombwa.

Guhindura izina

ya: Na: Gushigikira. ku. 2 - ya:.

Byahinduwe

Gufungura - Inkomoko na. - Kohereza,, na Gishya ku.

Inyandiko y'Iyemezabuguzi

A Umushinga Kuva: $5 / Mo i ya:, Na: Oya Cyangwa; i Kigenga ni ya: Bwite Koresha. na "na - Ibikorwaremezo Koresha".

Gufungura Inkomoko

Urugero,, na

KokoroKokoro

Free

Lightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.

Bihagaritse 5/5

kugirango: 2. 0 - Ubwiza Kigenga Urugero:, Kuri - Inturo:

Gushaka Kokoro

PiperPiper

Free

A fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.

Bihagaritse 3/5

kugirango: -, ya: Na -

Gushaka Piper

VITSVITS

Free

Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech.

Bihagaritse 3/5

kugirango: Byakoreshejwe ku

Gushaka VITS

BarkBark

Standard

Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.

Guca umurongo 4/5

kugirango: MIT — unique audio generation capabilities beyond standard TTS

Gushaka Bark

Tortoise TTSTortoise TTS

Premium

Multi-voice text-to-speech focused on quality with autoregressive architecture.

Guca umurongo 5/5 Guca umurongo

kugirango: 2. 0 - Kinini Ubwiza, Indango

Gushaka Tortoise TTS

OpenVoiceOpenVoice

Premium

Instant voice cloning with granular control over style, emotion, and accent.

Bisanzwe 4/5 Guca umurongo

kugirango: Gufungura - Inkomoko Na: Imisusire Igenzura

Gushaka OpenVoice

Gufungura Inkomoko

Cyangwa Gukoresha

1

Gufungura - Inkomoko

Agatabo Bya 20 + Gufungura - Inkomoko Udushushondanga. Udushushondanga Ipaji: i,,, na -.

2

in Mucukumbuzi

Test any model directly on TTS.ai without installing anything. Our GPU servers handle processing so you can evaluate quality before committing to self-hosting.

3

Cyangwa

Urugero Kuva: na Gukoresha, Cyangwa Koresha ya:. - Cyuzuye Igenzura;.

4

Porogaramu

Ikoresha: - Imisusire Cyangwa API. Urugero Itangira: A Imisusire na ya: - Ikoresha:.

Igenzura ry'Inyandikonyakwirema

License of each model on TTS.ai

Ubwoko bw'inyandiko Izina ry'idosiye Ikoresha: Ihinduramiterere Ubuturo Gushigikira
Kokoro Apache 2.0 Bya ngombwa
Piper MIT ; Amasezerano Bitari ngombwa
VITS MIT Bitari ngombwa
MeloTTS MIT Bitari ngombwa
Chatterbox MIT Bitari ngombwa
Tortoise TTS Apache 2.0 Bya ngombwa
StyleTTS 2 MIT Bitari ngombwa
OpenVoice MIT Bitari ngombwa
Sesame CSM Apache 2.0 Bya ngombwa
Orpheus Llama 3.2 "Built with Llama"
Spark TTS CC BY-NC-SA 4.0 Na - Ikoresha: Bya ngombwa
OuteTTS CC BY-NC-SA 4.0 Na - Ikoresha: Bya ngombwa
Gushaka

API

Cyangwa Twebwe i

ku

Every model on TTS.ai is available as an open-source project on GitHub or Hugging Face. Download the weights, install the dependencies, and run inference on your own GPUs. You have full control over latency, privacy, and scaling.

  • Ibyatanzwe Ibanga - Inyumvo Oya Seriveri:
  • Nyuma Itangira Iboneza
  • ku Ibyatanzwe
  • Ibikoresho
  • Ihuzagihe,, na

Use TTS.ai Hosted API

Igihe Kuri Byose 20 + Udushushondanga Gihinguranya A UMWE., Urugero: Ibyahinduwe:, Umurongo, na. Urufunguzo Kuri buri Urugero: - Oya Kuri Kuyobora.

  • Bya ngombwa
  • 20 + Gihinguranya Rimwe
  • Urugero Ihuzagihe Na
  • 99. 9% Na:
  • kugirango Koresha
Gukoresha API

Tangira & vendorShortName; Cyangwa -

Cyangwa Kwinjiza porogaramu in

Option 1: TTS.ai Hosted API Byoroheje 
import requests

response = requests.post("https://api.tts.ai/v1/tts", json={
    "text": "Open source TTS with a simple API.",
    "model": "kokoro",
    "voice": "af_heart",
    "format": "wav"
}, headers={"Authorization": "Bearer YOUR_API_KEY"})

with open("output.wav", "wb") as f:
    f.write(response.content)
2: - Na: Igenzura ryuzuye 
# Install Kokoro locally
pip install kokoro

# Generate speech on your own GPU
import kokoro

pipeline = kokoro.KPipeline(lang_code="a")
generator = pipeline("Hello from your own server!", voice="af_heart")
for i, (gs, ps, audio) in enumerate(generator):
    kokoro.save(audio, f"output_{i}.wav")
Inyandiko

Gufungura Inkomoko,

Gufungura - Inkomoko

Urwego rworoheje

$0

ku Kwiyandikisha

  • 4 Gufungura - Inkomoko
  • kugirango Shingiro Koresha
  • Bwite - Ikoresha:

Gutangira

$9

Inyuguti Ukwezi

  • Gufungura - Inkomoko
  • Guhindura izina
  • Uburenganzira bw' umukoresha

By'ingirakamaro

$29

Inyuguti Ukwezi

  • Ibyahiswemo
  • Udushushondanga
  • Gushigikira
Kugenzura...

Ibibazo bizwa kenshi

Bigyanye Gufungura Inkomoko Umwandiko Kuri

Yes, every model on TTS.ai is open source, and most use MIT or Apache 2.0. A few use other licenses, including some licensed for non-commercial use only, which are marked "Personal and non-commercial use only" in the voice picker. Each model page lists its license.

Gufungura - Inkomoko. 2. 0 & Ongera na Amahinduka NIBA Guhindura... i Inyandikoporogaramu. ni Na:. Ibicuruzwa -.

. Urugero -. i Urugero Kuva:, Kwinjiza porogaramu, Iyimura Urugero, na Gukoresha. Inyandiko ya: Urugero -,, na Verisiyo.

ku Urugero. Oya (). na 1 - 2. Bisanzwe Udushushondanga 4. na 8. Gukoresha Udushushondanga.

. Gufungura - Inkomoko Kwemera Ihinduramiterere -. nka - na - IYANDIKA. Udushushondanga ku Ijwi Ibyatanzwe Kuri Kurema Kugena Cyangwa Ibikorwa: ya:.

Gufungura - Inkomoko Udushushondanga (, 2,) NONEAHA BIHUYE Cyangwa Bicuruzwa Nka na Google in Ubuziranenge. Bya Bicuruzwa ni na Gushigikira, OYA Audio Ubuziranenge.

Some have been removed: XTTS/XTTS-v2 (Coqui's CPML, non-commercial), F5-TTS (CC-BY-NC, non-commercial) and Higgs-v2 (Boson License, restrictive). A few remaining models and voices, such as Spark TTS, OuteTTS and most Piper voices, are licensed for non-commercial use only; they are marked "Personal and non-commercial use only" in the voice picker, so use a different voice for commercial projects.

.. Kwemera Biturutse. Kohereza Ibisobanuro:, Ijwi ya: Gishya, Inyandikoporogaramu, na Inyandiko. Urugero: ya: na Gikora.

Udushushondanga ku - Ikibazo na Gukuramo Ryari: Kuri Gusangiza Ububiko. Seriveri: 20 + Udushushondanga ku 4 (Gusa:) ikoresha Gikora Itangira. -, A UMWE 3 - 5 Udushushondanga.

Ishusho Cyangwa. Igikubo, A Kugena Iboneza Na: ya:. Seriveri: Nka A Indango Ishyirwaho ry' ibikorwa.

3. 10 - 3. 12. () 3. 11. Kugira inama 3. 12 ya: Udushushondanga. Udushushondanga ya: Verisiyo.

If you self-host, mostly yes: MIT and Apache 2.0 licenses explicitly allow commercial use, and most models here use them, so you can build SaaS products, mobile apps, games and services with no licensing fees or royalties. Check the license on each model page first, because a few models and voices are non-commercial. Audio generated on TTS.ai itself follows your plan: personal use on the free tier, commercial use on any paid plan.
5.0/5 (1)

Twebwe?

Gufungura Inkomoko

20+ open-source models, each with its license listed. Use our API or self-host, the choice is yours.

Kwiyandikisha Kugenzura...