Hiring: TTS Engineer for Emotionally Expressive Voice Synthesis (Paid, Precision Role)

[SunzGawd]

We’re seeking a precision-oriented TTS engineer for a real-world voice deployment focused on emotional fidelity and behaviorally adaptive voice output. This is a paid engagement under a well-defined execution protocol.

---

### ✅ Ideal Experience

• Fine-tuning or adapting TTS models for expressiveness/emotion
  (e.g., OpenVoice v2, Bark, Tortoise, Coqui)
• Working knowledge of phoneme alignment tools
  (e.g., Montreal Forced Aligner or equivalent)
• Familiarity with prosody control, speaker conditioning, or multi-take variation
• Experience with emotion-tagged audio datasets
• Ability to deliver under constraint, this is about focus and fidelity, not bulk

---

### 🛠️ Preferred Tools / Frameworks

• OpenVoice v2 (primary framework in use)
• Montreal Forced Aligner (MFA) or equivalent
• PyTorch, HuggingFace, Python, FFmpeg, SoX

---

### 🎯 Scope

• You’ll work with a curated emotion-tagged dataset across 3-take variations
• Task: fine-tune emotional modulation and prosody on top of OpenVoice v2
• Deliver adaptive voice outputs aligned to structured expressive targets

❗ This is not generic voice cloning or API-wrapping.
We're building deep emotional control for real agent-based deployment.

---

### ⏱️ Execution Cap (Important)

The entire fine-tuning phase is capped at 12 hours total.
This is not an evaluation sprint, it’s the actual execution scope.
The asset stack and alignment framework are already pre-built.
We’re looking for clarity, decisiveness, and technical precision.

---

### 📩 How to Apply

• Check my GitHub profile bio, contact email is listed there.
• Include:
  • Brief overview of relevant experience
  • Any GitHub/audio/demo links (if available)
  • Your availability over the next 4–6 weeks

We're moving quickly and looking for someone who can own this piece with control and confidence.

Thanks.
Sunz