Open TTS Tracker: Open-Access Text-to-Speech Models

Open TTS Tracker is a dataset tracking open-access and open-source Text-to-Speech models. The dataset, created by Pendrokar, was last updated on February 20, 2026. It is hosted on Hugging Face and aims to be a central resource for awareness of these models.

Use Cases

• Discovering new open-source TTS models based on the curated list mentioned in the description.
• Comparing TTS model capabilities based on the sorting criteria described.
• Identifying candidate models for speech synthesis projects based on the open-access focus.

Strengths

• Tracks models sorted by the amount of capabilities, as stated in the description.
• Explicitly focuses on open-access and open-source models, providing a specific niche.
• Last update timestamp (2026-02-20 14:55:28) is provided.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Hugging Face dataset created by Pendrokar.

Collection Method

Likely manually curated from public sources and community contributions, as suggested by the call for pull requests.

Freshness

Last updated 2026-02-20 14:55:28; freshness should be verified.