---
type: "post"
id: "patientdesk-ai-released-antalia-2-mini-a-7-1cc483"
slug: "patientdesk-ai-released-antalia-2-mini-a-7-1cc483"
title: "PatientDesk AI released Antalia-2 Mini , a 7.62M-parameter Turkish TTS model under Apache-2.0."
description: "**Thesis:** A very small, permissively licensed Turkish TTS model makes local deployment and integration more accessible, while its single voice and model-card-only evaluation bound what can be inferred about its readiness."
retrieval_nugget: "**Thesis:** A very small, permissively licensed Turkish TTS model makes local deployment and integration more accessible, while its single voice and model-card-only evaluation bound what can be inferred about its readiness."
published_at: "2026-10-11"
updated_at: "2026-10-11"
record_date: "2026-10-11"
date_kind: "published_at"
topics: []
source_urls: ["https://huggingface.co/cloud0day3/antalia-mini"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:patientdesk-ai-released-antalia-2-mini-a-7-1cc483"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:cd74df96d421610941dad43c643139e4cab0190e5fc2b16ba6ecfdcec97223f1","reviewed_at":"2026-10-11T14:03:32.448Z","source_evidence_count":1,"verified_claim_count":4,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":4,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"A very small, permissively licensed Turkish TTS model makes local deployment and integration more accessible, while its single voice and model-card-only evaluation bound what can be inferred about its readiness.","observed_facts":[{"text":"The Hugging Face model card identifies Antalia-2 Mini as a 7.62-million-parameter Turkish TTS model with 48 kHz output and claims faster-than-real-time CPU performance.","source_urls":["https://huggingface.co/cloud0day3/antalia-mini"]},{"text":"The model card says code and weights are Apache-2.0 licensed and describes a browser demo running locally with ONNX Runtime Web.","source_urls":["https://huggingface.co/cloud0day3/antalia-mini"]},{"text":"The card describes one synthetic male voice and reports no real-speaker recordings in its training data.","source_urls":["https://huggingface.co/cloud0day3/antalia-mini"]},{"text":"The authors report similar WER results with EMA Lightning in their harness, alongside differences in naturalness scores by metric and band.","source_urls":["https://huggingface.co/cloud0day3/antalia-mini"]}],"mechanism":"An included Turkish text normalizer handles numbers, dates, times, amounts, abbreviations, URLs, and English or brand terms before synthesis; package, streaming, and browser-local paths provide routes to integrate or test the model.","why_now":"The release packages language-specific normalization, local execution options, and permissive licensing in a compact model instead of requiring a hosted endpoint.","implications":["Builders can test Turkish speech generation in CPU-based or local workflows without first relying on a hosted service.","The single-voice scope and project-reported evaluation mean broad suitability and quality remain unestablished."],"evidence_boundary":"Release specifications and evaluation results are taken from the project's Hugging Face model card and have not been independently verified.","watch_conditions":["Independent tests should establish how intelligibility and naturalness hold across varied Turkish text, devices, and real application audio conditions."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied for this specific Turkish TTS release, so this begins a distinct analytical record without asserting a related record."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/patientdesk-ai-released-antalia-2-mini-a-7-1cc483/","markdown":"https://newruntime.com/posts/patientdesk-ai-released-antalia-2-mini-a-7-1cc483.md","json":"https://newruntime.com/posts/patientdesk-ai-released-antalia-2-mini-a-7-1cc483.json"}
---

# PatientDesk AI released Antalia-2 Mini , a 7.62M-parameter Turkish TTS model under Apache-2.0.

## Retrieval answer

**Thesis:** A very small, permissively licensed Turkish TTS model makes local deployment and integration more accessible, while its single voice and model-card-only evaluation bound what can be inferred about its readiness.

**Thesis:** A very small, permissively licensed Turkish TTS model makes local deployment and integration more accessible, while its single voice and model-card-only evaluation bound what can be inferred about its readiness.

**Mechanism:** An included Turkish text normalizer handles numbers, dates, times, amounts, abbreviations, URLs, and English or brand terms before synthesis; package, streaming, and browser-local paths provide routes to integrate or test the model.

Antalia-2 Mini has 7.62 million parameters and produces 48 kHz audio; the model card says it runs faster than real time on a CPU. It provides a Python package, streaming and batched synthesis, and a browser demo that uses ONNX Runtime Web locally. The weights and code use Apache-2.0.

**Why now:** The release packages language-specific normalization, local execution options, and permissive licensing in a compact model instead of requiring a hosted endpoint. The model card reports comparisons with EMA Lightning, including similar WER in its harness, but also differing naturalness scores across measures and bands. Those results are useful as a starting point, not proof of performance across applications or users.

**First implication:** Builders can test Turkish speech generation in CPU-based or local workflows without first relying on a hosted service.

The model card describes one synthetic male voice and says its training data contains no recordings of real speakers. That narrows one potential concern, but does not establish broad voice coverage, robustness, or suitability for every deployment. **Evidence boundary:** Release specifications and evaluation results are taken from the project's Hugging Face model card and have not been independently verified.

**First watch condition:** Independent tests should establish how intelligibility and naturalness hold across varied Turkish text, devices, and real application audio conditions.

This starts a distinct analytical record because no prior New Runtime record was supplied for this specific Turkish TTS release; no related record is asserted.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)