Seeking TTS Engineer with Emotional Fine-Tuning Experience (OpenVoice v2, MFA, Prosody Control)

[SunzGawd]

We’re looking for an experienced TTS engineer to assist with an advanced speech synthesis project focused on emotionally expressive voice output. This is a paid engagement involving real-world agent deployment, with emphasis on fine-grained emotional control and output integrity.

---

### ✅ Desired Experience:

• Fine-tuning TTS models for expressiveness/emotion (e.g., OpenVoice v2, Bark, Tortoise, Coqui)
• Experience with phoneme alignment tools (e.g., MFA or equivalent)
• Familiarity with prosody control, speaker adaptation, or multi-take variation
• Comfort working with structured emotional audio datasets
• Able to contribute to real-world use cases, not just research demos

---

### 🛠️ Preferred Tools / Frameworks:

• OpenVoice v2 / Bark / Tortoise
• MFA or forced alignment toolkits
• PyTorch, HuggingFace, Python, FFmpeg, SoX

---

### 🔍 The Role:

This role involves:

• Working with a curated emotion-tagged voice dataset
• Modulating emotional expression across defined behavioral cues
• Supporting model alignment, tuning, and evaluation

We're not looking for generic voice cloning or API wrapping, this is deep fine-tuning for emotional fidelity and response shaping.

### 📩 How to Apply

If you're interested. Check bio, contact info, and provide:

• A brief overview of relevant experience
• Any GitHub/audio/demo links
• Your availability over the next 4–6 weeks

We’re moving quickly and looking for someone who can own this piece of execution with precision.

Thanks!
Sunz