whereismyai
VoxCPM
VoxCPM is an open source text-to-speech model that generates multilingual speech, creative voice designs, and voice cloning at 48kHz high-fidelity.
VoxCPM is a tokenizer-free text-to-speech system designed for high-fidelity audio generation. It supports over 30 languages and offers tools for mixed-language speech and creative voice design. The model generates expressive intonation and natural rhythm, making it suitable for audiobooks, game NPC performance, and vocal character creation. Users access the models on Hugging Face and the source code via GitHub. It emphasizes open source development, allowing for fine-tuning and community-driven expansion.
VoxCPM at a glance
- Best for: Social media creator, Writer
- Runs on: Web
- Pricing: Free and open source
- Released: September 2025
- Category: AI audio tool
- Website: voxcpm.com
Key features
- Supports 30+ languages
- 48kHz high-fidelity audio generation
- Tokenizer-free speech synthesis
- Mixed-language speech capability
- Controllable voice creativity and design
- Expressive intonation and emotional layering
Use it for
- Creating expressive audiobooks
- Generating game NPC character performances
- Designing custom vocal styles
- Producing multilingual speech content
Alternatives to VoxCPM
- Voicebox — Perform voice cloning and generation entirely on local hardware.
- Fish Audio — Provides studio-grade voice cloning and text-to-speech with emotion control.
- MOSS-TTS — Delivers zero-shot voice cloning and fine-grained pronunciation control.
- MisoTTS — Generates high-quality conversational speech using an RVQ Transformer architecture.
- AuK — It handles zero-shot TTS, editing, and enhancement via natural language.
- DiffSinger — It uses a shallow diffusion mechanism for singing voice synthesis and text-to-speech.
- Applio — Runs locally with open-source code and no telemetry.
- GPT-SoVITS — It allows high-fidelity voice cloning with as little as one minute of data.
- Eleven v4 and Eleven v4 Turbo — Generates low latency expressive speech with real time streaming.
- IndexTTS — Supports zero-shot voice cloning with multi-language emotion and speed control.
- Respeecher — Engineered for professional production workflows with ethical standards.
- VoiceStudio — Runs locally on your machine with no account, cloud connection, or API keys required.
All VoxCPM alternatives