whereismyai
EmotiVoice
EmotiVoice is an open-source text-to-speech engine that generates multi-voice, emotion-controlled audio in English and Chinese.
EmotiVoice is an open-source text-to-speech engine capable of synthesizing speech with specific emotional attributes like happiness, excitement, sadness, and anger. The system supports both English and Chinese languages and offers over 2,000 different voice profiles for generation. Users can influence speech output using emotional prompts and style controls, including pitch, speed, and energy. The software includes a web-based interface for interaction and an OpenAI-compatible HTTP API for batch generation and integration. It supports custom voice cloning using personal data and provides a scripting interface for developers.
EmotiVoice at a glance
- Best for: Social media creator, Writer
- Runs on: Web, macOS, Linux, Windows, API, open source, self-hosted
- Pricing: Free
- Released: November 2023
- Category: AI audio tool
- Website: github.com/netease-youdao/EmotiVoice
Key features
- Emotional synthesis control
- Support for over 2,000 distinct voices
- English and Chinese language support
- OpenAI-compatible HTTP API
- Personal voice cloning capabilities
- Web interface for interactive usage
- Scripting interface for batch generation
Use it for
- Generating emotional synthetic speech for media
- Creating custom voice clones from personal audio data
- Integrating text-to-speech into applications via HTTP API
Alternatives to EmotiVoice
- Fish Audio — Provides studio-grade voice cloning and text-to-speech with emotion control.
- VoxCPM — Provides tokenizer-free multilingual speech with controllable voice creativity.
- 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.
- VibeVoice — Process long-form audio up to 60 minutes in a single pass.
- MisoTTS — Generates high-quality conversational speech using an RVQ Transformer architecture.
- GPT-SoVITS — It allows high-fidelity voice cloning with as little as one minute of data.
- MOSS-TTS — Delivers zero-shot voice cloning and fine-grained pronunciation control.
- ElevenLabs — Natural AI voices, with 10,000+ voices in 70+ languages
- VoiceStudio — Runs locally on your machine with no account, cloud connection, or API keys required.
- TTS WebUI — It offers a free web interface with over 30 AI models for audio generation.
- Applio — Runs locally with open-source code and no telemetry.
All EmotiVoice alternatives