Freie KI Text in die Rede
22+ Open-Source-Modelle, 100+ Stimmen, 32+ Sprachen. Kein Konto erforderlich.
Alles, was Sie für Voice KI benötigen
26 Werkzeuge mit 24+ Open-Source-KI-Modellen
22+ KI-Stimmemodelle
Die umfassendste Sammlung von Open-Source-TTS-Modellen in einer Plattform
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.
Am besten für: High-quality TTS with minimal latency, streaming applications
Versuchen Sie kostenlosPiper 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.
Am besten für: Quick previews, accessibility, and embedded applications
Versuchen Sie kostenlosVITS 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.
Am besten für: General-purpose text-to-speech with natural prosody
Versuchen Sie kostenlosMeloTTS 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.
Am besten für: Production applications needing fast, multilingual TTS
Versuchen Sie kostenlosBark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Entwickler: Suno · Lizenz: MIT
Versuch es.Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Entwickler: Suno · Lizenz: MIT
Versuch es.CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Entwickler: Alibaba (Tongyi Lab) · Lizenz: Apache 2.0
Versuch es.Dia TTS Standard
Multi-Lautsprecher-Dialog-Generierungsmodell, das natürliche Gespräche zwischen Lautsprechern erzeugt.
Entwickler: Nari Labs · Lizenz: Apache 2.0
Versuch es.Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Entwickler: Hugging Face · Lizenz: Apache 2.0
Versuch es.IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Entwickler: Index Team · Lizenz: Apache 2.0
Versuch es.Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Entwickler: SparkAudio · Lizenz: Apache 2.0
Versuch es.GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Entwickler: RVC-Boss · Lizenz: MIT
Versuch es.Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Entwickler: Canopy Labs · Lizenz: Llama 3.2 Community
Versuch es.Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Entwickler: Alibaba (Qwen) · Lizenz: Apache 2.0
Versuch es.CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Sprachen: en, zh, ja, ko, fr, de, it, es
KlonstimmeIndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Sprachen: en, zh
KlonstimmeSpark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Sprachen: en, zh
KlonstimmeGPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Sprachen: en, zh, ja, ko
KlonstimmeChatterbox
Modernste Zero-Shot-Stimme, die mit Emotionskontrolle von Resemble KI klont.
Sprachen: en
KlonstimmeTortoise TTS
Multi-Voice-Text-to-Speech konzentrierte sich auf Qualität mit autoregressiver Architektur.
Sprachen: en
KlonstimmeOpenVoice
Instant voice cloning with granular control over style, emotion, and accent.
Sprachen: en, zh, ja, ko, fr, de, es, it
KlonstimmeQwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Sprachen: en, zh, ja, ko, de, fr, ru, pt, es, it
KlonstimmeEntwickler-Erste API
OpenAI-kompatible REST API. Ein Endpunkt, 22+ Modelle. Streaming-Unterstützung für Echtzeit-Anwendungen.
- OpenAI-kompatibles Format
- Streaming TTS für Echtzeit-Apps
- Batch-Verarbeitung für große Arbeitsplätze
- Webhook-Benachrichtigungen
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)
Einfache, transparente Preisgestaltung
Starten Sie frei, skalieren Sie, wie Sie wachsen.
Frei
50 Gutschriften
- Kokoro, Piper, VITS, MeloTTS
- 500 Zeichen-Grenze
- 3 gen/Stunde (kein Konto)
Starter
500 Gutschriften/Monat
- Alle 22+ Modelle
- 5.000 Zeichen-Grenze
- Stimme Klonen
Pro
2000 Gutschriften/Monat
- Alles im Starter
- API-Zugriff
- Vorrangige Verarbeitung
Unternehmen
10 000 Gutschriften/Monat
- Alles in Pro
- Bulk API
- Prioritätswarteschlange
Häufig gestellte Fragen
Verwenden Sie KI-Stimme heute
Werden Sie Schöpfer, Entwickler und Unternehmen mit TTS.ai