Fri AI Tekst til tale
22+ open source-modeller, 100+ stemmer 32+ sprog. Ingen konto påkrævet.
Alt hvad du behøver til stemme AI
26 værktøjer drevet af 24+ open source-AI-modeller
22+ AI-stemmemodeller
Den mest omfattende samling af open source TTS-modeller i én 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.
Bedst til: High-quality TTS with minimal latency, streaming applications
Prøv gratisPiper 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.
Bedst til: Quick previews, accessibility, and embedded applications
Prøv gratisVITS 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.
Bedst til: General-purpose text-to-speech with natural prosody
Prøv gratisMeloTTS 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.
Bedst til: Produktionsapplikationer, der kræver hurtige, flersprogede TTS
Prøv gratisBark Standard
Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.
Udvikler: Suno · Licens: MIT
Prøv det.Bark Small Standard
Lighter version of Bark with faster inference and lower memory usage.
Udvikler: Suno · Licens: MIT
Prøv det.CosyVoice 2 Standard
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Udvikler: Alibaba (Tongyi Lab) · Licens: Apache 2.0
Prøv det.Dia TTS Standard
Multi-højttaler dialog generation model, der skaber naturlige samtaler mellem højttalere.
Udvikler: Nari Labs · Licens: Apache 2.0
Prøv det.Parler TTS Standard
Describe the voice you want in natural language and Parler generates matching speech.
Udvikler: Hugging Face · Licens: Apache 2.0
Prøv det.IndexTTS-2 Standard
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Udvikler: Index Team · Licens: Apache 2.0
Prøv det.Spark TTS Standard
Voice cloning TTS with controllable emotion and speaking style via prompts.
Udvikler: SparkAudio · Licens: Apache 2.0
Prøv det.GPT-SoVITS Standard
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Udvikler: RVC-Boss · Licens: MIT
Prøv det.Orpheus Standard
Human-level emotional TTS model trained on 100K hours of speech data.
Udvikler: Canopy Labs · Licens: Llama 3.2 Community
Prøv det.Qwen3 TTS Standard
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Udvikler: Alibaba (Qwen) · Licens: Apache 2.0
Prøv det.CosyVoice 2
Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.
Sprog: en, zh, ja, ko, fr, de, it, es
KlonstemmeIndexTTS-2
Zero-shot TTS with fine-grained emotion control and high expressiveness.
Sprog: en, zh
KlonstemmeSpark TTS
Voice cloning TTS with controllable emotion and speaking style via prompts.
Sprog: en, zh
KlonstemmeGPT-SoVITS
Few-shot voice cloning TTS that replicates any voice from just 5 seconds of audio.
Sprog: en, zh, ja, ko
KlonstemmeChatterbox
Den nyeste nul-shot stemmekloning med følelsesmæssig kontrol fra Resemble AI.
Sprog: en
KlonstemmeTortoise TTS
Multi-stemme tekst-til-tale fokuseret på kvalitet med autoregressiv arkitektur.
Sprog: en
KlonstemmeOpenVoice
Øjeblikkelig stemmekloning med granuleret kontrol over stil, følelser og accent.
Sprog: en, zh, ja, ko, fr, de, es, it
KlonstemmeQwen3 TTS
Alibaba's multilingual TTS with voice cloning, preset voices, and voice design from text.
Sprog: en, zh, ja, ko, de, fr, ru, pt, es, it
KlonstemmeUdvikler- første API
OpenAI-kompatibel REST API. Et endpoint, 22 + modeller. Streaming støtte til real-time applikationer.
- OpenAI- kompatibelt format
- Streaming af TTS til real-time apps
- Batchforarbejdning til store job
- Webhook- meddelelserName
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)Enkel, gennemsigtig prissætning
Start gratis. Skalér som du vokser.
Fri
50 kreditter
- Kokoro, Piper, VITS, MeloTTS
- 500 tegngrænse
- 3 gen/time (ingen konto)
Pro
2.000 kreditter/måned
- Alt i starten
- API- adgang
- Prioriteret behandling
Ofte stillede spørgsmål
Begynd at bruge AI stemme i dag
Deltag skabere, udviklere og virksomheder, der bruger TTS.ai