2025/05/20 - CSM is availabile natively in Hugging Face Transformers as of version 4.52.1 2025/03/13 - We are releasing the 1B CSM variant. The checkpoint is hosted on Hugging Face. CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes. A fine-tuned variant of CSM powers the interactive voice demo shown in our blog post. A hosted HuggingFace space is also available for testing audio generation. CSM supports full-graph compilation with CUDA graphs! CSM can be fine-tuned using Transformers' Trainer. Does this…
Zonos-v0.1-transformer is an open-weight model for text to speech from Zyphra, released under Apache License 2.0. It has 1.6B parameters. At 16-bit it needs about 3.9 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 160.1k downloads a month.
alt="Title card" style="width: 500px; Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.
Parameters1.6B
Context—
Weights3.2 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads160.1k
Runs On
What it takes to serve Zonos-v0.1-transformer (1.6B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 3.2 GB | 3.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.6 GB | 1.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.8 GB | 1.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 9, 2026.
Zonos-v0.1-transformer on every accelerator the SAVRN Index prices, at every precision
Model Card
By Zyphra, published under apache-2.0, revision 9d8331fc49cb.
Zonos-v0.1
Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.
Our model enables highly natural speech generation from text prompts when given a speaker embedding or audio prefix, and can accurately perform speech cloning when given a reference clip spanning just a few seconds. The conditioning setup also allows for fine control over speaking rate, pitch variation, audio quality, and emotions such as happiness, fear, sadness, and anger. The model outputs speech natively at 44kHz.
For more details and speech samples, check out our blog here
We also have a hosted version available at playground.zyphra.com/audio
Zonos follows a straightforward architecture: text normalization and phonemization via eSpeak, followed by DAC token prediction through a transformer or hybrid backbone. An overview of the architecture can be seen below.
Usage
Python
Identity and Version
- Repository
- Zyphra/Zonos-v0.1-transformer
- Publisher
- Zyphra
- Task
- Text to speech
- Modality
- Audio
- Library
- zonos
- Parameters
- 1.6B parameters
- Languages
- Not stated by the source
- Revision
- 9d8331fc49cb5ba8aad2bb56cafd809c66598f4e
- First published
- 2025-02-06
- Last updated
- 2025-06-03
Files and Weights
4 files, 3.2 GB in total. The weights are 1 file totalling 3.2 GB in safetensors.
Weights1 file · 3.2 GB
Configuration1 file · 2.5 KB
Documentation1 file · 5.5 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.2 GB | 4ac68319d6b8 |
| config.json | Configuration | 2.5 KB | — |
| README.md | Documentation | 5.5 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 3.2 GB
Download from Zyphra
Released by Zyphra through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.2 GB |
| 16-bit | 3.2 GB |
| 8-bit | 1.6 GB |
| 4-bit | 0.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Compare Zonos-v0.1-transformer
Questions About Zonos-v0.1-transformer
How much GPU memory does Zonos-v0.1-transformer need?
About 3.9 GB at 16-bit and 1 GB at 4-bit: the weights (1.6B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Zonos-v0.1-transformer on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use Zonos-v0.1-transformer commercially?
Yes. Zonos-v0.1-transformer is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs. In addition, the models feature strong contextual understanding, enabling adaptive control of tone, speaking rate, and emotional expression based on instructions and text semantics, and they show markedly improved robustness to noisy input text. Key features: Intelligent Text Understanding and Voice Control: Supports speech generation driven by natural language instructions, allowing for flexible control over multi-dimensional acoustic attributes such as timbre, emotion, and prosody.…
We release Qwen3-TTS, a series of powerful speech generation models developed by Qwen, offering comprehensive support for voice cloning, voice design, ultra-high-quality human-like speech generation, and natural language-based voice control. Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles. Key features: Install the qwen-tts Python package from PyPI: Zero-shot speech generation on the Seed-TTS test set (Word Error Rate (WER, ↓)): If you find our paper and code useful in your research, please consider giving a star and citation
DuDE is a full-duplex conversation TTS (text-to-speech) model that generates two speakers together from an XML dialogue. It supports turn-taking, backchannels, and overlapping speech, with a separate voice for each speaker. The output is a 24 kHz stereo WAV: speaker A on the left, speaker B on the right. DuDE first self-distills Qwen3-TTS on independent utterances to adapt a shared backbone to two interleaved channels. It is then fine-tuned on approximately 1,922 hours of synchronized Seamless Interaction conversations to learn turn-taking, backchannels, and overlapping speech. The XML frontend resolves turn dependencies into interleaved text inputs. Reference-speaker embeddings condition…
MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental sound effects, and real‑time streaming TTS. When a single piece of audio needs to sound like a real person, pronounce every word accurately, switch speaking styles across content, remain stable over tens of minutes, and support dialogue, role‑play, and real‑time interaction, a single TTS model is often not enough. The MOSS‑TTS Family breaks the workflow into five production‑ready models that can be…
VibeVoice-Realtime is a lightweight real‑time text-to-speech model supporting streaming text input and robust long-form speech generation. It can be used to build realtime TTS services, narrate live data streams, and let different LLMs start speaking from their very first tokens (plug in your preferred model) long before a full answer is generated. It produces initial audible speech in ~300 ms (hardware dependent). ▶ Watch demo video (Launch your own realtime demo via the websocket example in Usage) Although the model is primarily built for English, we found that it still exhibits a certain level of multilingual capability—and even performs reasonably well in some languages. We provide nine…