Qwen3-TTS vs Kokoro: which self-hosted OpenAI-compatible TTS to pick

Описание и применение

Qwen3‑TTS обеспечивает лучшую качество и выразительность речи, но требует больше памяти и времени, в то время как Kokoro‑82M быстрее и занимает меньше памяти, подходя для реального времени.

Задача

Choosing a self-hosted TTS model that balances voice quality, expressiveness, latency, and memory footprint.

Результат

Qwen3-TTS delivers superior voice quality and expressive controls at the cost of higher latency and memory usage, while Kokoro-82M offers faster, low-footprint inference suitable for real-time or resource-constrained scenarios.

Рабочий процесс

• 1. Deploy Kokoro-82M or Qwen3-TTS via Railway one-click templates or Docker.
• 2. Measure latency and memory usage on target hardware.
• 3. Compare voice quality and expressiveness (e.g., emotion markup, multi-speaker presets).
• 4. Choose Qwen3-TTS for higher quality and expressiveness, or Kokoro for real-time speed and low memory.
• 5. Switch between models by changing the base URL of the OpenAI-compatible /v1/audio/speech endpoint.

Доказательства

Qwen3-TTS wins, clearly. I ran both directly against each other. It's a 1.7B model versus Kokoro's 82M, and it shows — tone and pacing hold together much better across longer narration.

Источник

Kokoro is faster than realtime on a shared vCPU and needs about 1GB RAM. Qwen3-TTS is CPU-bound — realtime factor around 2, so not real-time — and wants 4-6GB RAM.

Источник