VieNeu-TTS
pnnbao-ump基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 9
VieNeu-TTS-0.3B
pnnbao-ump基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗VieNeu-TTS-0.3B-q4-gguf
pnnbao-ump**VieNeu-TTS-0.3B-Q4-0-GGUF** is a **Q4_0** quantized version of VieNeu-TTS-0.3B. This model is specifically optimized to run directly on the **CPU**, providing extremely fast speech synthesis without the need for a dedicated GPU. Training high-quality TTS models requires significant GPU resources. If you find this model useful, please consider supporting the development: eSpeak NG is **mandatory** for phonemization. - **Windows:** Download `.msi` from eSpeak NG Releases. - **macOS:** `brew install espeak` - **Linux:** `sudo apt install espeak-ng`
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗VieNeu-TTS-q4-gguf
pnnbao-ump基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗VieNeu-TTS-v2
pnnbao-ump**VieNeu-TTS-v2** is the next generation of Vietnamese TTS, designed for **Natural Communication**, **Podcasts**, and **Bilingual (En-Vi) Code-switching**. > [!IMPORTANT] > **What's new in V2:** > - **10,000+ Hours Data:** Trained on a massive bilingual dataset for unparalleled naturalness. > - **Multi-Speaker Conversation:** Support for podcast-style scripts with distinct voices and emotional nuances. > - **Seamless Code-switching:** High-quality English integration within Vietnamese sentences. > - **Instant Voice Cloning:** Still supports cloning with just **3-5 seconds** of audio. This project features the flagship **VieNeu-TTS-v2** architecture: - **VieNeu-TTS-v2 (0.3B):** Optimized for high-fidelity bilingual speech and long-form content. - **VieNeu-TTS-v2-Turbo:** Optimized for ultra-low latency and CPU deployment using GGUF.
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗VieNeu-TTS-v2-Turbo
pnnbao-ump基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗VieNeu-TTS-v2-Turbo-GGUF
pnnbao-ump基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗VieNeu-TTS-v3-Nano
pnnbao-ump> [!WARNING] > **Preview release — still under active testing.** VieNeu-TTS v3 Nano is an experimental, lightweight model. It has known shortcomings (see *Limitations* below), its quality is **noticeably lower than v3 Turbo**, and weights, voices and the API may still change between revisions. **VieNeu-TTS v3 Turbo remains the default and recommended model.** Reach for Nano only when Turbo is too slow on your hardware or when you are deploying on a phone / edge device. **VieNeu-TTS v3 Nano** is a **48M-parameter flow-matching TTS model** for Vietnamese, built for **edge devices and weak CPUs**: old laptops, mini PCs, ARM single-board computers and Android phones. It ships as a handful of small **ONNX** graphs (≈280 MB at runtime), runs **torch-free on ONNX Runtime**, loads in about 3 seconds and synthesizes at roughly **3× the speed of v3 Turbo** on the same CPU. It is a different architecture from v3 Turbo (a non-autoregressive flow model instead of an LLM-style autoregressive backbone), which is where the speed comes from — and also where the quality gap comes from. It supports **6 built-in preset voices**, inline **emotion cues** (`[cười]`, `[thở dài]`, `[hắng giọng]`) and outputs **24 kHz** audio.
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗VieNeu-TTS-v3-Turbo
pnnbao-ump**VieNeu-TTS v3 Turbo** is the next generation of Vietnamese TTS — **48 kHz** high-fidelity speech, **23 built-in preset voices** across three regions (North / Central / South), **instant voice cloning**, **real-time streaming** with an **OpenAI-compatible API** (16 concurrent streams on one RTX 3060), inline **emotion cues**, and seamless **bilingual (En–Vi) code-switching**. The reference implementation is the **`vieneu` Python SDK (v3.7.1)**. Its minimal install is **torch-free**: on CPU everything runs on **ONNX Runtime** (PyTorch is never imported), and on a CUDA machine it auto-switches to the PyTorch engine with **automatic batching** and a **continuous-batching stream scheduler** — same API, no code change. > [!IMPORTANT] > **What's new in SDK v3.7:** > - **GPU streaming with continuous batching** — `infer_stream` on CUDA runs on one CUDA graph shared by every caller: first audio in **~115 ms**, **16 concurrent streams under 200 ms** on a single RTX 3060 (32 max). > - **OpenAI-compatible streaming API + Docker** — `POST /v1/audio/speech` (`pcm`/`wav`, chunked or SSE) works with the OpenAI SDK, Pipecat, LiveKit; `docker compose --profile api-gpu` / `api-cpu`. Numbers, sizing and CPU-only notes: docs/streaming.md. > - **23 preset voices** covering North / Central / South, both genders and several reading characters (default: `Minh Quân`). > - **LoRA fine-tuning** of v3 Turbo on one consumer GPU. > - Since 3.3: torch-free voice cloning on CPU, optional **int8** CPU backbone (`Vieneu(precision="int8")`, ~2× faster; fp32 is the default), sliding-window repetition penalty.
Input Text→ Output Audio
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
MODEL HANDBOOK
Understand before you choose
How should API prices be compared?+
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.