Gratis AI Tekst naar spraak
22+ open-source modellen, 100+ stemmen, 32+ talen. Geen account vereist.
Alles wat je nodig hebt voor Voice AI
26 gereedschappen aangedreven door 24+ open-source AI modellen
22+ AI Voice Modellen
De meest uitgebreide collectie van open-source TTS-modellen in één platform
Kokoro Free
Kokoro is an 82 million parameter text-to-speech model that punches well above its weight class. Despite its tiny size, it produces remarkably natural and expressive speech. Kokoro supports multiple languages including English, Japanese, Chinese, and Korean with a variety of expressive voices. It runs incredibly fast — generating audio nearly 100x faster than real-time on a GPU.
Beste voor: High-quality TTS with minimal latency, streaming applications
Probeer vrijPiper Free
Piper is a lightweight text-to-speech engine developed by Rhasspy that uses VITS and larynx architectures. It runs entirely on CPU, making it ideal for edge devices, home automation, and applications requiring offline TTS. With over 100 voices across 30+ languages, Piper delivers natural-sounding speech at real-time speeds even on a Raspberry Pi 4.
Beste voor: Quick previews, accessibility, and embedded applications
Probeer vrijVITS Free
VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. It adopts variational inference augmented with normalizing flows and an adversarial training process, achieving a significant improvement in naturalness.
Beste voor: General-purpose text-to-speech with natural prosody
Probeer vrijMeloTTS Free
MeloTTS by MyShell.ai is a multilingual TTS library supporting English (American, British, Indian, Australian), Spanish, French, Chinese, Japanese, and Korean. It is extremely fast, processing text at near real-time speed on CPU alone. MeloTTS is designed for production use and supports both CPU and GPU inference.
Beste voor: Productietoepassingen die snel, meertalig TTS nodig hebben
Probeer vrijBark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Ontwikkelaar: Suno · Licentie: MIT
Probeer het.Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Ontwikkelaar: Suno · Licentie: MIT
Probeer het.CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Ontwikkelaar: Alibaba (Tongyi Lab) · Licentie: Apache 2.0
Probeer het.Dia TTS Standard
Multi-luidspreker dialoogvenster generatie model dat natuurlijke gesprekken tussen luidsprekers creëert.
Ontwikkelaar: Nari Labs · Licentie: Apache 2.0
Probeer het.Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Ontwikkelaar: Hugging Face · Licentie: Apache 2.0
Probeer het.IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Ontwikkelaar: Index Team · Licentie: Apache 2.0
Probeer het.Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Ontwikkelaar: SparkAudio · Licentie: Apache 2.0
Probeer het.GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Ontwikkelaar: RVC-Boss · Licentie: MIT
Probeer het.Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Ontwikkelaar: Canopy Labs · Licentie: Llama 3.2 Community
Probeer het.Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Ontwikkelaar: Alibaba (Qwen) · Licentie: Apache 2.0
Probeer het.CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Talen: en, zh, ja, ko, fr, de, it, es
KloonstemIndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Talen: en, zh
KloonstemSpark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Talen: en, zh
KloonstemGPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Talen: en, zh, ja, ko
KloonstemTortoise TTS
Multi-voice text-to-speech gericht op kwaliteit met autoregressieve architectuur.
Talen: en
KloonstemOpenVoice
Instant voice cloning with granular control over style, emotion, and accent.
Talen: en, zh, ja, ko, fr, de, es, it
KloonstemQwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Talen: en, zh, ja, ko, de, fr, ru, pt, es, it
KloonstemOntwikkelaar-eerste API
OpenAI-compatibele REST API. Eén eindpunt, 22+ modellen. Streaming ondersteuning voor real-time toepassingen.
- OpenAI-compatibel formaat
- Streaming TTS voor real-time apps
- Batchverwerking voor grote jobs
- Webhook notificaties
import requests
response = requests.post(
"https://api.tts.ai/v1/tts/",
headers={"Authorization": "Bearer sk-tts-xxx"},
json={
"model": "kokoro",
"text": "Hello from TTS.ai!",
"voice": "af_bella",
}
)
with open("output.mp3", "wb") as f:
f.write(response.content)Eenvoudige, transparante prijzen
Begin vrij, schuin naarmate je groeit.
Vrij
50 credits
- Kokoro, Piper, VITS, MeloTTS
- 500 tekenlimiet
- 3 gen/uur (geen rekening)
Starter
500 kredieten/maand
- Alle 22+ modellen
- 5.000 tekenlimiet
- Stemklonen
Pro
2000 kredieten/maand
- Alles in Starter
- API-toegang
- Prioritaire verwerking
Onderneming
10.000 credits/maand
- Alles in Pro
- Bulk API
- Prioriteitswachtrij
Veelgestelde vragen
Start met het gebruik van AI Voice vandaag
Sluit je aan bij makers, ontwikkelaars en bedrijven die TTS.ai gebruiken