# eSpeak NG vs Parler-TTS

| Attribute | eSpeak NG | Parler-TTS |
|---|---|---|
| **Vioscale score** | 49.5 (26% (low)) | 28.6 (17% (low)) |
| activity.commits_last_30d | 36 | 0 |
| adoption.dependent_repos | - | 0 |
| adoption.github_stars | 6,762 | 5,586 |
| deployment.options | `{"self_hosted":true}` | `{"self_hosted":true}` |
| description.long | A lightweight open source text-to-speech engine that converts written text into spoken audio using formant synthesis. Available as a command-line tool and C/library for integration across Linux, Windows, Android, and other platforms. | An inference and training library for speech synthesis models, available as an open-source project distributed via pip. |
| integrations.count | 3 | - |
| integrations.list | `[{"name":"MBROLA"},{"name":"SAPI5"},{"name":"C API library integration"}]` | - |
| language.primary | C | Python |
| license.spdx | GPL-3.0 | Apache-2.0 |
| platform.support | `{"cli":true,"mac":true,"linux":true,"android":true,"windows":true}` | `{"cli":true}` |
| pricing | `{"type":"open_source","summary":"Free and open source","freeTier":true,"sourceUrl":"https://github.com/pricing","retrievedAt":"2026-08-19T22:01:16.060Z"}` | `{"type":"open_source","freeTier":true,"sourceUrl":"https://github.com/pricing","retrievedAt":"2026-08-19T22:25:09.827Z"}` |
| pricing.free_tier | yes | yes |
| pricing.model | commercial | commercial |
| pricing.price_level | free | free |
| pricing.transparent | yes | - |
| release.cadence_days | 799 | - |
| release.history | `[{"url":"https://github.com/espeak-ng/espeak-ng/releases/tag/1.52.0","date":"2024-12-12T13:47:27Z","type":"stable","version":"1.52.0"},{"url":"https://github.com/espeak-ng/espeak-ng/releases/tag/1.51","date":"2022-04-02T19:43:39Z","type":"stable","version":"1.51"},{"url":"https://github.com/espeak-ng/espeak-ng/releases/tag/1.50","date":"2019-12-02T12:34:16Z","type":"stable","version":"1.50"},{"url":"https://github.com/espeak-ng/espeak-ng/releases/tag/1.49.2","date":"2017-09-24T09:37:08Z","type":"stable","version":"1.49.2"},{"url":"https://github.com/espeak-ng/espeak-ng/releases/tag/1.49.1","date":"2017-01-21T21:20:08Z","type":"stable","version":"1.49.1"},{"url":"https://github.com/espeak-ng/espeak-ng/releases/tag/1.49.0","date":"2016-09-10T10:20:46Z","type":"stable","version":"1.49.0"}]` | - |
| security.scorecard | 4.5 | - |
| security.vulnerabilities | - | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=pypi&package_name=parler-tts&per_page=100","last_12m":0,"max_severity":null}` |

## Capabilities (Text To Speech)

| Capability | eSpeak NG | Parler-TTS |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Voice cloning | - | - |
| Zero shot cloning | - | - |
| Streaming synthesis | - | - |
| Ssml support | - | - |
| Emotion style control | - | - |
| On device offline | - | - |
| Open source | - | - |
| Watermarking provenance | - | - |
| Cloning consent verification | - | - |

*Source: Vioscale. Generated 2026-09-01T15:15:04.000Z. "-" = undocumented, not absent.*