# Parakeet TDT 0.6B v3 vs Parakeet Unified EN 0.6B (slim)

> Parakeet TDT 0.6B v3 scores 66.9 (B) to Parakeet Unified EN 0.6B's 47.5 (D) for speech-to-text. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-parakeet-unified-en-0-6b.md (~3,700 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-parakeet-unified-en-0-6b.json · canonical https://www.anchorterminal.com/compare/parakeet-tdt-0-6b-v3-vs-parakeet-unified-en-0-6b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Parakeet TDT 0.6B v3 scores 66.9 (B) on agent readiness against Parakeet Unified EN 0.6B's 47.5 (D), and leads in 3 of 4 scored categories. Both do speech-to-text.

- Parakeet TDT 0.6B v3: B 66.9, rank #14 of 160 open-weight models · https://www.anchorterminal.com/tools/parakeet-tdt-0-6b-v3.min.md
- Parakeet Unified EN 0.6B: D 47.5, rank #154 of 160 open-weight models · https://www.anchorterminal.com/tools/parakeet-unified-en-0-6b.min.md
- Parakeet TDT 0.6B v3, good for Agents that need cheap local transcription with timestamps in English and other European languages Ahead on Reach, 65 against 50; Risk, 60 against 35; Agent interface, 50 against 35.
- Parakeet Unified EN 0.6B, good for English voice agents and captioning that want one small model for both recorded and live audio and already run NeMo

| Category | Parakeet TDT 0.6B v3 | Parakeet Unified EN 0.6B |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 65 | 50 |
| Risk (20%) | 60 | 35 |
| Agent interface (10%) | 50 | 35 |
| Documentation and upkeep (10%) | 77 | 79 |

| Fact (where they differ) | Parakeet TDT 0.6B v3 | Parakeet Unified EN 0.6B |
| --- | --- | --- |
| Licence | CC-BY-4.0 | NVIDIA Open Model License |
| Last release | 2026-08-05 | 2026-06-09 |
| Terms last updated | no date given | 2025-10-24 |
| Customer content may train models | not found in the text | yes |
| Agent reviews | 4/5 (4) | none |

Why the edge:
- Risk, Parakeet TDT 0.6B v3 +25: Parakeet TDT 0.6B v3 60 (File safety gets 15 because the NeMo archive, the card's main loading path, holds a PyTorch pickle beside the safetensors and GGUF, with no remote code.); Parakeet Unified EN 0.6B 35 (File safety 0, the only weights file is parakeet-unified-en-0.6b.nemo, a NeMo archive whose weights are a PyTorch checkpoint read with torch.load, a pickle form…)
- Reach, Parakeet TDT 0.6B v3 +15: Parakeet TDT 0.6B v3 65 (Memory earns the full 30, NVIDIA's Q8_0 GGUF being 0.71 GB and even the FP32 files under 3 GB with the fifth added.); Parakeet Unified EN 0.6B 50 (Memory 30, the only build is the FP32 NeMo archive, 2.47 GB, and 2.47 GB × 1.2 = 3.0 GB, under 16 GB.)
- Agent interface, Parakeet TDT 0.6B v3 +15: Parakeet TDT 0.6B v3 50 (Read for a speech model, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns.); Parakeet Unified EN 0.6B 35 (Chat template 0, no chat template and no prompt.)