# Speechmatics vs whisper.cpp

**Leader by vioscaleAI score:** Speechmatics

| Attribute | Speechmatics | whisper.cpp |
|---|---|---|
| **vioscaleAI score** | 73.4 (54% (medium)) | 57.7 (34% (low)) |
| activity.commits_last_30d | - | 100 |
| adoption.dependent_repos | - | 18 |
| adoption.github_stars | - | 54,417 |
| content.faq | `[{"answer":"Speechmatics provides speech recognition that converts audio to text with real-time and batch processing. It supports 55+ languages, identifies multiple speakers, can run on-device or in the cloud, and does not log transcription data by default. It is indexed under Speech To Text.","source":"https://www.speechmatics.com/","question":"What is Speechmatics?","confidence":0.6},{"answer":"Speechmatics offers a free tier, so you can start without paying. Paid plans start at $0.24. Pricing changes often, so verify at source before relying on it.","source":"https://www.speechmatics.com/pricing","question":"Is Speechmatics free?","confidence":0.6},{"answer":"Speechmatics supports the web and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://www.speechmatics.com/","question":"What platforms does Speechmatics support?","confidence":0.6},{"answer":"Yes. Speechmatics can be deployed cloud / SaaS and on-premise, so it does not have to run on the vendor's infrastructure.","source":"https://www.speechmatics.com/","question":"Can Speechmatics be self-hosted?","confidence":0.6},{"answer":"We have confirmed 7 integrations for Speechmatics, including Stenograph CATalyst VP, Adobe Premiere, Zapier, Twilio, Python SDK, JavaScript SDK and .NET SDK. This is what we could verify from public sources, so the vendor may support others we have not indexed.","source":"https://www.speechmatics.com/","question":"What does Speechmatics integrate with?","confidence":0.6},{"answer":"We have independently confirmed SOC 2, ISO 27001, HIPAA and GDPR for Speechmatics. Certifications we do not list are ones we have not been able to verify from public sources, which is not the same as Speechmatics not holding them. Always confirm compliance directly before you rely on it.","source":"https://www.speechmatics.com/company/articles-and-news/your-essential-guide-to-voice-ai-compliance-in-todays-digital-landscape","question":"What security certifications does Speechmatics have?","confidence":0.7},{"answer":"Speechmatics is available worldwide. Its primary market is the United States.","source":"https://www.speechmatics.com/","question":"Where is Speechmatics available?","confidence":0.5}]` | `[{"answer":"An open-source library that provides speech-to-text transcription capabilities, ported from OpenAI's Whisper model. It supports various hardware accelerators and runs on multiple platforms with a command-line interface. It is indexed under Speech To Text.","source":"https://github.com/pricing","question":"What is whisper.cpp?","confidence":0.6},{"answer":"whisper.cpp is open source, so it can be self-hosted and used at no licence cost. It is released under the MIT licence. Pricing changes often, so verify at source before relying on it.","source":"https://github.com/pricing","question":"Is whisper.cpp free to use?","confidence":0.6},{"answer":"whisper.cpp supports macOS, Linux, iOS, Android and a command-line interface. Platforms we have not confirmed are simply not listed here rather than ruled out.","source":"https://github.com/pricing","question":"What platforms does whisper.cpp support?","confidence":0.6},{"answer":"Yes. whisper.cpp can be deployed self-hosted, so it does not have to run on the vendor's infrastructure.","source":"https://github.com/pricing","question":"Can whisper.cpp be self-hosted?","confidence":0.6},{"answer":"Yes. whisper.cpp is published under the MIT licence, a permissive licence that generally allows commercial use and modification. Licence terms can change between releases, so verify against the repository for the version you intend to use.","source":"https://github.com/ggerganov/whisper.cpp","question":"Is whisper.cpp open source?","confidence":0.95}]` |
| deployment.options | `{"cloud":true,"hybrid":true,"on_prem":true,"self_hosted":true}` | `{"on_prem":true,"self_hosted":true}` |
| description.long | A speech-to-text service that converts audio to transcripts, supporting real-time and batch processing with high accuracy, speaker identification, and support for 55+ languages. | An open-source C/C++ implementation that brings OpenAI's Whisper speech recognition to local devices. It executes entirely offline without network connectivity and integrates into various hardware platforms from mobile to specialized computing systems. |
| features.capabilities | `{"fine_tuning":true,"pii_redaction":true,"vertical_model":true,"word_timestamps":true,"custom_vocabulary":true,"offline_on_device":true,"real_time_streaming":true,"speaker_diarization":true,"punctuation_formatting":true}` | `{"open_source":true,"word_timestamps":true,"offline_on_device":true}` |
| integrations.count | 4 | - |
| integrations.list | `[{"name":"Stenograph CATalyst VP"},{"name":"Adobe Premiere"},{"name":"Zapier"},{"name":"Twilio"},{"name":"Python SDK"},{"name":"JavaScript SDK"},{"name":".NET SDK"},{"name":"Stenograph","native":true,"category":"legal"},{"name":"Adobe","native":true},{"name":"Microsoft Azure","native":true,"category":"cloud","direction":"bidirectional"},{"name":"LiveKit","native":true,"direction":"bidirectional"},{"name":"Vonage","native":true,"category":"communications","direction":"bidirectional"},{"name":"Veritone","native":true}]` | - |
| language.primary | - | C++ |
| license.spdx | - | MIT |
| market.availability | `{"hqCountry":"GB","primaryMarkets":["GB","US","EU"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"cli":true,"web":true}` | `{"cli":true,"ios":true,"linux":true}` |
| pricing | `{"type":"usage","plans":[{"free":false,"name":"Melia 1 (General purpose)","summary":"$0.12/hr","features":["55+ languages","Code-switching","Language hints","Language labeling","Custom dictionary","Smart formatting","Word-level timings"],"components":[{"per":{"qty":1,"unit":"hour"},"kind":"metered","amount":0.12,"currency":"USD"}],"description":"Multilingual model that transcribes 56 languages and switches language mid-sentence","contactSales":false},{"free":false,"name":"Enhanced","summary":"$0.38/hr","features":["Single-language maximum accuracy","Custom dictionary","Advanced punctuation"],"components":[{"per":{"qty":1,"unit":"hour"},"kind":"metered","amount":0.38,"currency":"USD"}],"description":"Highest accuracy model for single-language transcription with advanced punctuation and custom dictionary support","contactSales":false},{"free":false,"name":"Medical (Oak 1)","summary":"$0.15/hr","features":["Clinical conversations and dictation","Healthcare vocabulary","55+ languages"],"components":[{"per":{"qty":1,"unit":"hour"},"kind":"metered","amount":0.15,"currency":"USD"}],"description":"Domain-specific model designed for clinical language with healthcare vocabulary and multilingual support","contactSales":false},{"free":false,"name":"Standard","summary":"$0.23/hr","features":["High volume and cost-sensitive workloads"],"components":[{"per":{"qty":1,"unit":"hour"},"kind":"metered","amount":0.23,"currency":"USD"}],"description":"Cost-efficient model with same features as Enhanced at lower rate","contactSales":false},{"free":false,"name":"Linden 1 (Voice agents)","summary":"Contact for pricing","description":"Speech-to-text model purpose-built for voice agents with built-in turn detection","contactSales":true},{"free":false,"name":"Text to Speech","summary":"$0.011 per 1,000 characters","features":["First 1 million characters free"],"components":[{"per":{"qty":1000,"unit":"characters"},"kind":"metered","amount":0.011,"currency":"USD"}],"description":"Natural, low-latency speech synthesis for voice AI use cases","contactSales":false}],"addOns":[{"name":"PII redaction"},{"name":"Translation","components":[{"per":{"qty":1,"unit":"hour"},"kind":"metered","amount":0.49,"currency":"USD"}]},{"name":"Chapters","components":[{"per":{"qty":1,"unit":"hour"},"kind":"metered","amount":0.3,"currency":"USD"}]},{"name":"Topics","components":[{"per":{"qty":1,"unit":"hour"},"kind":"metered","amount":0.15,"currency":"USD"}]},{"name":"Summaries","components":[{"per":{"qty":1,"unit":"hour"},"kind":"metered","amount":0.09,"currency":"USD"}]},{"name":"Sentiment"},{"name":"Audio alignment"}],"summary":"From $0.12/hr for speech-to-text. Free tier with $100 credits.","currency":"USD","freeTier":true,"sourceUrl":"https://www.speechmatics.com/pricing","retrievedAt":"2026-10-12T16:14:29.240Z","startingPrice":{"unit":"characters","amount":0.011,"currency":"USD"}}` | `{"type":"open_source","freeTier":true,"sourceUrl":"https://github.com/pricing","retrievedAt":"2026-08-19T21:33:54.410Z"}` |
| pricing.free_tier | yes | yes |
| pricing.model | freemium | open_source |
| pricing.price_level | low | free |
| pricing.starting_price | `{"amount":0.011,"currency":"USD"}` | - |
| pricing.transparent | yes | yes |
| release.cadence_days | - | 14 |
| release.history | - | `[{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.5","date":"2026-10-06T17:39:17Z","type":"stable","version":"v1.9.5"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/b5454","date":"2026-10-06T16:51:27Z","type":"prerelease","version":"b5454"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.4","date":"2026-09-11T05:31:55Z","type":"stable","version":"v1.9.4"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/b5130","date":"2026-09-11T05:29:10Z","type":"prerelease","version":"b5130"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/b5127","date":"2026-09-10T11:55:26Z","type":"prerelease","version":"b5127"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.3","date":"2026-08-20T11:39:36Z","type":"prerelease","version":"v1.9.3"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/b4938","date":"2026-08-20T11:33:19Z","type":"stable","version":"b4938"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.2","date":"2026-08-04T15:31:37Z","type":"stable","version":"v1.9.2"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.1","date":"2026-06-19T05:53:19Z","type":"stable","version":"v1.9.1"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.9.0","date":"2026-06-17T10:19:21Z","type":"stable","version":"v1.9.0"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.7","date":"2026-06-16T10:59:32Z","type":"stable","version":"v1.8.7"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.6","date":"2026-06-02T06:22:27Z","type":"stable","version":"v1.8.6"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.5","date":"2026-05-29T12:07:04Z","type":"stable","version":"v1.8.5"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.4","date":"2026-03-19T15:08:38Z","type":"stable","version":"v1.8.4"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.3","date":"2026-01-15T11:27:48Z","type":"stable","version":"v1.8.3"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.2","date":"2025-10-15T08:32:18Z","type":"stable","version":"v1.8.2"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.1","date":"2025-10-12T10:18:45Z","type":"stable","version":"v1.8.1"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.8.0","date":"2025-09-30T18:44:14Z","type":"stable","version":"v1.8.0"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.7.6","date":"2025-06-25T13:50:49Z","type":"stable","version":"v1.7.6"},{"url":"https://github.com/ggml-org/whisper.cpp/releases/tag/v1.7.5","date":"2025-04-02T14:34:08Z","type":"stable","version":"v1.7.5"}]` |
| security.certifications | `[{"name":"SOC 2 Type II","level":"Type II","status":"active"},{"name":"ISO/IEC 27001:2022","status":"active"}]` | - |
| security.disclosure_policy | yes | - |
| security.gdpr | yes | - |
| security.hipaa | yes | - |
| security.iso27001 | yes | - |
| security.scorecard | - | 5.1 |
| security.soc2 | yes | - |
| security.trust_center | https://www.speechmatics.com/company/articles-and-news/compliance-breaches-share-price | https://github.com/security |
| security.vulnerabilities | - | `{"count":0,"source":"https://advisories.ecosyste.ms/api/v1/advisories?ecosystem=go&package_name=github.com%2Fggerganov%2Fwhisper.cpp%2Fbindings%2Fgo&per_page=100","last_12m":0,"max_severity":null}` |

## Capabilities (Speech To Text)

| Capability | Speechmatics | whisper.cpp |
|---|:--:|:--:|
| **Capabilities** |  |  |
| Real time streaming | ✓ | - |
| Speaker diarization | ✓ | - |
| Custom vocabulary | ✓ | - |
| Fine tuning | ✓ | - |
| Word timestamps | ✓ | ✓ |
| Punctuation formatting | ✓ | - |
| Pii redaction | ✓ | - |
| Vertical model | ✓ | - |
| Offline on device | ✓ | ✓ |
| Open source | - | ✓ |

*Source: vioscaleAI. Generated 2026-10-16T19:15:11.473Z. "-" = undocumented, not absent.*