- 1. Conclusion: The Voices We Chose
- 2. TTS Overview
- 1. What Is TTS?
- 2. Ways to Specify a Voice, and Terminology
- 3. Overview of the Three TTS Models
- 1. Qwen3-TTS
- 2. Chatterbox Multilingual V3
- 3. Irodori-TTS
- 4. Comparison Method
- 1. The Tool Used for the Comparison
- 2. The Characters to Compare
- 3. The Variations Generated
- 4. Listening to Candidates in HTML
- 5. Fixing a Candidate as Master Audio
- 5. Comparison Results
- 1. Comparing with Audio Samples
- 1. Elekibear's Japanese Voice Comparison
- 2. Elekibear's English Voice Comparison
- 3. Plasmo's Japanese Voice Comparison
- 4. Plasmo's English Voice Comparison
- 2. Results by Feature
- 3. Measured Generation Speed (RTF)
- 4. The Final Configuration
- 6. In Closing
- Home
- 20260924_01_local_tts
[Local TTS] Creating and Comparing Original Voices with Qwen3, Irodori, and Chatterbox
PythonGenerative AITTS
2026-09-24

PythonGenerative AITTS
2026-09-24
Share this post
Follow the author
Your follow really keeps me going!
Your follow really keeps me going!
Related Posts

[PySide6] Building a GUI Tool That Handles Multiple Local TTS Models [TTS Toolkit]
2026-09-23

[Suno AI] Tips for Making the Song You Really Want, Without Settling for Raw AI Output
2026-09-13

[PySide6] Building a GUI Tool to Transcribe Audio and Get Lyric Timestamps with Whisper [Whisper Toolkit]
2026-09-07

[UE5.8] [Houdini] I Devoted My Summer Vacation to a Crab - Making a 3D MV with AI Generation, UE and Houdini
2026-08-23

[Blender5.2] Trying Out 3D Model Creation with Blender MCP [Codex / GPT5-SOL]
2026-08-09

[ComfyUI] Getting the Hunyuan3D Wrapper Running on an RTX 50 Setup
2026-08-09

[Obsidian] Notes on Setting Up Attachments, Multi-Device Sync, and Other Initial Settings
2026-08-08

[PySide6] Building a General-Purpose Launcher Tool for Registering and Running Scripts [Command Launcher]
2026-06-07



