Qwen TTS · General · Qwen3-TTS

Qwen3-TTS 1.7B CustomVoice: Specs, GPU requirements, hosting & deployment

Qwen3-TTS 1.7B CustomVoice is a current Speech Generation release in the Qwen TTS family, certified from its immutable official source revision.

Calculate recommendation Customise a model Enterprise Model Transformation Compare this model

Technical deployment reference illustration for Qwen3-TTS 1.7B CustomVoice — Reference deployment flow; exact architecture facts are listed separately.

Total parameters1.9B

Active parametersN/A / Not directly comparable

Context windowN/A / Not directly comparable

Release statusCurrent · Current

ArchitectureText-to-speech transformer

ModalitiesText, Audio

LicenseApache License 2.0

Deployment stateDeployable with certified configuration

Commercial stateCommercial Use Allowed

Release date2026-01-21

Architecture, strengths and use cases

Qwen3-TTS 1.7B CustomVoice is an official self-hostable Qwen Audio and speech release. It uses Text-to-speech transformer with 1.916B. Exact checkpoint, license, runtime, and hardware evidence is tied to the verified upstream revision.

Qwen3-TTS 1.7B CustomVoice uses Text-to-speech transformer with 1.916B. Pipeline and configuration fields are reported only where the official source publishes them.

Verified Text-to-speech transformer architecture

Official checkpoint and pipeline evidence

Official BF16, Unknown checkpoint coverage

Self-hosted Audio and speech workloads

Controlled model evaluation

Production deployment planning

Certified checkpoints and quantizations

Only exact, source-certified variants attached to this release are shown.

Qwen3-TTS-12Hz-1.7B-CustomVoice

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Official · BF16 · safetensors

Runtime certified: Transformers

Precision / quantization	Format	Bits	Publisher trust	Deployment state
BF16	safetensors	16	Official	Runtime certified

Recommended hardware

Use only the listed runtime configurations with the exact checkpoint precision. Hardware sizing considers resident pipeline memory, runtime overhead, input and output dimensions, batch size, and safety headroom.

Estimated weight memory3.68 GB

Runtime overhead5.38 GB

Total with safety margin11.23 GB

Recommended best value

1× NVIDIA A100 SXM 80GB

80 GB total VRAM · nvlink

68.77 GB headroom · Available

USD 915 / month

Lowest-cost viable

1× NVIDIA L4 24GB

24 GB total VRAM · pcie

12.77 GB headroom · Available

USD 250 / month

Highest performance

1× NVIDIA H200 SXM 141GB

141 GB total VRAM · nvswitch

129.77 GB headroom · Limited capacity

USD 2,345 / month

License and self-hosting considerations

The exact pipeline and selected precision must fit on the chosen GPUs. Requirements vary with resolution, duration, batch size, modalities, and runtime; language-model KV-cache rules are not applied.

Qwen3-TTS 1.7B CustomVoice is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.

Commercial Use Allowed. The official license permits commercial use; its obligations still apply.

Alternatives and sibling variants

Qwen3-TTS-12Hz-1.7B-CustomVoice

Release timeline

qwen/qwen-tts/qwen3-tts-1-7b-customvoice

3 Sept 2026

Source details

Official source

Source revision: fd4a64b56cacd8e4c15855840a1aced18ece7aa5e58a63be5bd4fc4a9f3236f9

Frequently asked questions

How much VRAM does Qwen3-TTS 1.7B CustomVoice require?

The estimate uses the certified checkpoint, precision, runtime, workload dimensions, batch size, and domain-specific overhead.

Which runtimes support Qwen3-TTS 1.7B CustomVoice?

Certified upstream runtime evidence is available for transformers.

Can Qwen3-TTS 1.7B CustomVoice be used commercially?

The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.

Official references

Last verified: 2026-08-26