Downloads · 30 days
0
qwen3-tts-openvino-voice-design
BC202/qwen3-tts-openvino-voice-design
qwen3-tts-openvino-voice-design is a text-to-speech model from BC202. Use it when you need text read aloud. The card lists the license as apache-2.0.
This repository stores exported OpenVINO IR artifacts for qwen3-tts-openvino runtime downloads.
Access
Public
Updated Jul 24, 2026
Repo size
45.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin9.6 GB · 99%
At a glance
- Task
- Text-to-Speech
- License
- apache-2.0
- Access
- Public
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026
- SHA
- 68c9bf34
Model card
From the Hugging Face model README
Qwen3-TTS OpenVINO IR
This repository stores exported OpenVINO IR artifacts for qwen3-tts-openvino runtime downloads.
Layout
openvino_realtime/voice_design/: voice_design OpenVINO IRopenvino_realtime/custom_voice/: custom_voice OpenVINO IRopenvino_realtime/base/: VoiceClone/Base OpenVINO IR
The runtime sidecar downloads these files automatically when a mode is missing locally.
Profile
Current public profile: runtime-minimal.
For runtime-minimal, each mode keeps only the validated low-memory production graph set:
- text and codec embedding graphs
int8_sym_batch_fused_gqapaged-KV batch talker seed graph- cached standalone subcode graph, executed row-by-row by the online scheduler
- streaming decoders
c0_t8,c25_t12, andc25_t24 - VoiceClone/Base additionally keeps
speech_encoder,speaker_encoder, andcode_frame_embedding
Legacy full decoders, alternate streaming chunks, no-cache talker graphs, batch-fused decode graphs, sampled batch subcode graphs, fixed-bucket/unroll diagnostic graphs, and OpenVINO compile caches are intentionally not published here.
- Task
- Text-to-Speech
- License
- apache-2.0
- Created
- Jul 24, 2026
- Updated
- Jul 24, 2026