The Next Generation
of Speech Synthesis.
We're building a leaner TTS architecture that achieves competitive naturalness at a fraction of the training data and cost of industry leaders.
Hear It For Yourself
Our V0 model, trained on 45,000 hours — less than 1% of industry-standard datasets. Type anything and synthesize speech in real time.
Tontaube V0 is an early research model. Improved versions are coming to the app and API soon.
Trained on 1% of the Data. 10× Faster.
Early experiments showing significant efficiency gains over industry-standard approaches.
Generation speed was compared against the leading open source model Qwen-TTS on single sequence audio generation, using the same RTX 3090 GPU.
Build with Tontaube
A high-speed, cost-efficient voice generation API powered by our architecture. Clone any voice from a single audio file and generate long-form speech at 10× real-time speed.
- One-shot voice cloning
- 0.10× real-time factor — 1 min audio in ~6 s
- ~2% of ElevenLabs pricing
import tontaube
client = tontaube.Client(api_key="your_key")
# Clone any voice from a single audio file
voice_id = client.create_voice(
audio_file="sample.mp3"
)
# Generate speech — 0.10× real-time factor
audio = client.generate_speech(
text="The next generation of speech synthesis.",
voice_id=voice_id
)
Tontaube for iOS & Android
Our audiobook and voice cloning app — already in the hands of thousands of listeners. Convert any document to audio, clone your voice, and stream from a public domain library.
- PDF, EPUB & document conversion
- Free voice cloning
- 30,000+ AI audiobooks
Interested in Investing?
We've proven the architecture at prototype scale and are seeking investment to scale compute, data, and the team.