# VibeVoice-1.5B-hf by VibeVoice Community (Unofficial) Source: https://savrn.com/models/vibevoice-1-5b-hf Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve VibeVoice-1.5B-hf (2.7B 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 | 5.4 GB | 6.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 2.7 GB | 3.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 1.4 GB | 1.6 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 22, 2026. [VibeVoice-1.5B-hf on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/vibevoice-1-5b-hf/gpus) ## Model Card By VibeVoice Community (Unofficial), published under mit, revision d4cd82eb4371. ### VibeVoice-1.5B-hf (Transformers-compatible version) VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a Large Language Model (LLM) to understand textual context and dialogue flow, and a diffusion head to generate high-fidelity acoustic details. The model can synthesize speech up to 90 minutes long with up to 4 distinct speakers, surpassing the typical 1-2 speaker limits of many prior models. Technical Report: [VibeVoice Technical Report](https://savrn.com/papers/vibevoice-technical-report) Project Page: [microsoft/VibeVoice](https://microsoft.github.io/VibeVoice) This model was contributed by [Eric Bezzam](https://huggingface.co/bezzam). ### Usage ### Setup Until VibeVoice is in Transformers as of v5.17.0: [Read the full model card (2,295 words)](https://savrn.com/models/vibevoice-1-5b-hf/card) ## Configuration Architecture VibeVoiceForConditionalGeneration Context length (tokens) 65,536 Layers 28 Hidden size 1,536 Feed-forward size 8,960 Attention heads 12 Key/value heads 2 Vocabulary size 151,936 Model type vibevoice ## Identity and Version Repository vibevoice/VibeVoice-1.5B-hf Publisher VibeVoice Community (Unofficial) Task Text to speech Modality Audio Library transformers Parameters 2.7B parameters Languages en, zh Revision d4cd82eb4371bf3e3d088e1ea7fa4eefb60449bf First published 2026-08-27 Last updated 2026-09-16 ## Files and Weights 13 files, 5.4 GB in total. The weights are 3 files totalling 5.4 GB in safetensors. Weights3 files · 5.4 GB Configuration4 files · 128.3 KB Tokenizer2 files · 11.4 MB Documentation1 file · 21.9 KB Other2 files · 156.4 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model-00001-of-00003.safetensors | Weights | 2.0 GB | a3b37bfffd84 | | model-00002-of-00003.safetensors | Weights | 2.0 GB | 6c560af42a0c | | model-00003-of-00003.safetensors | Weights | 1.4 GB | eeb349833fd1 | | config.json | Configuration | 3.2 KB | — | | generation_config.json | Configuration | 487 B | — | | model.safetensors.index.json | Configuration | 124.1 KB | — | | processor_config.json | Configuration | 511 B | — | | README.md | Documentation | 21.9 KB | — | | chat_template.jinja | Other | 2.4 KB | — | | figures/Fig1.png | Other | 154.0 KB | 64464f28380f | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 11.4 MB | 3fd169731d2c | | tokenizer_config.json | Tokenizer | 811 B | — | ## License and Download License mit Access Open weights, no gate Download size 5.4 GB [Download from VibeVoice Community (Unofficial)](https://huggingface.co/vibevoice/VibeVoice-1.5B-hf) Released by VibeVoice Community (Unofficial) through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Described by [arXiv:2412.08635](https://savrn.com/papers/multimodal-latent-language-modeling-with-next-token-diffusion) - Described by [arXiv:2508.19205](https://savrn.com/papers/vibevoice-technical-report) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 5.4 GB | | 16-bit | 5.4 GB | | 8-bit | 2.7 GB | | 4-bit | 1.4 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About VibeVoice-1.5B-hf ### How much GPU memory does VibeVoice-1.5B-hf need? About 6.5 GB at 16-bit and 1.6 GB at 4-bit: the weights (2.7B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run VibeVoice-1.5B-hf 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 VibeVoice-1.5B-hf commercially? Yes. VibeVoice-1.5B-hf is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included. ### What is VibeVoice-1.5B-hf's context length? 65,536 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text to speech ### [VibeVoice-1.5B](https://savrn.com/models/vibevoice-1-5b) [Microsoft](https://savrn.com/model-publishers/microsoft) VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a Large Language Model (LLM) to understand textual… Open weights mit 2.7B parameters transformers [View model](https://savrn.com/models/vibevoice-1-5b) Model · Text to speech ### [VibeVoice-1.5B](https://savrn.com/models/vibevoice-1-5b-2) [VibeVoice Community (Unofficial)](https://savrn.com/model-publishers/vibevoice) https://github.com/vibevoice-community/VibeVoice VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a… Open weights mit 2.7B parameters transformers [View model](https://savrn.com/models/vibevoice-1-5b-2) Model · Text to speech ### [VoxCPM2-q8](https://savrn.com/models/voxcpm2-q8) [Ryo Shimizu](https://savrn.com/model-publishers/shi3z) An INT8-quantized repack of openbmb/VoxCPM2, prepared so the model can be loaded and run entirely inside a web browser by shi3z/voxcpm2web (a WASM + WebGPU port of Nothing about the model architecture was changed. This repository exists to solve 1. wasm32 has a 4 GB address space. The upstream checkpoint is 4.27 GiB of weights plus a 359 MB audiovae.pth. 2. Quantizing during load costs VRAM you may not have. Doing it ahead of time means the browser never materializes the full-precision tensors at all. There is no separate audiovae file: the AudioVAE weights are already merged in, so a browser needs exactly one large download instead of two. Both rows produce applied=632 missing=0 unused=0… Open weights apache-2.0 2.4B parameters voxcpm-rs [View model](https://savrn.com/models/voxcpm2-q8) Model · Text to speech ### [VoxCPM2](https://savrn.com/models/voxcpm2) [OpenBMB](https://savrn.com/model-publishers/openbmb) VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data. - 30-Language Multilingual — No language tag needed; input text in any supported language directly - Voice Design — Generate a novel voice from a natural-language description alone (gender, age, tone, emotion, pace…); no reference audio required - Controllable Cloning — Clone any voice from a short clip, with optional style guidance to steer emotion, pace, and expression while preserving timbre - Ultimate Cloning — Provide reference audio + its transcript for audio-continuation cloning; every vocal nuance… Open weights apache-2.0 2.3B parameters voxcpm [View model](https://savrn.com/models/voxcpm2) Model · Text to speech ### [VoxCPM2](https://savrn.com/models/voxcpm2-2) [K1ng Tai](https://savrn.com/model-publishers/k1ngtai) VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data. - 30-Language Multilingual — No language tag needed; input text in any supported language directly - Voice Design — Generate a novel voice from a natural-language description alone (gender, age, tone, emotion, pace…); no reference audio required - Controllable Cloning — Clone any voice from a short clip, with optional style guidance to steer emotion, pace, and expression while preserving timbre - Ultimate Cloning — Provide reference audio + its transcript for audio-continuation cloning; every vocal nuance… Open weights apache-2.0 2.3B parameters voxcpm [View model](https://savrn.com/models/voxcpm2-2) Model · Text to speech ### [MOSS-VoiceGenerator](https://savrn.com/models/moss-voicegenerator) [OpenMOSS](https://savrn.com/model-publishers/openmoss-team) 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… Open weights apache-2.0 2.1B parameters 40,960 tokens [View model](https://savrn.com/models/moss-voicegenerator) ## VibeVoice Community (Unofficial) [All models and datasets](https://savrn.com/model-publishers/vibevoice) ## Versions - [d4cd82eb4371](https://savrn.com/models/vibevoice-1-5b-hf/versions/d4cd82eb4371) · current 2026-09-18 ## Explore More - [All text to speech models](https://savrn.com/models/tasks/text-to-speech) - [All models under mit](https://savrn.com/models/licenses/mit) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/vibevoice/VibeVoice-1.5B-hf) - [How the hub is built](https://savrn.com/model-hub/methodology)