Speechmatics vs ElevenLabs Scribe v2: Which Speech-to-Text API Delivers?

No. ElevenLabs offers speaker diarization in Scribe v2 (batch), but Scribe v2 Realtime doesn't support diarization. Speechmatics provides full real-time speaker diarization, with channel diarization also available. For live call analytics or voice agents, Speechmatics tells you who is speaking while they speak.

Speechmatics ranks ahead on overall transcription accuracy in head-to-head customer evaluations, including names and numerical data. Speechmatics is also rated stronger on non-English languages such as Arabic, Turkish, and Hebrew, where ElevenLabs Scribe underperforms.

Speechmatics offers true on-premises containers that run on CPU or GPU and can be deployed in secure, air-gapped networks. ElevenLabs offers private deployment of Scribe on Amazon SageMaker and Vertex AI, with on-premises deployment in early access on GPU servers with Confidential Computing support.

Phonetic custom dictionaries are a core, deeply integrated feature in Speechmatics. You can define how brand names, product names, and specialist terms are transcribed using phonetics. ElevenLabs Scribe offers keyterm prompting (up to 1,000 terms in batch, 50 in real-time), billed as an add-on, without phonetic spellings.

Speechmatics has purpose-built medical uplift models across English, French, German, Spanish, Danish, Norwegian, and Arabic-English bilingual. These are production-ready for clinical documentation and healthcare workflows — see the Humetrix case study for a proof point. ElevenLabs offers Scribe v2 Medical, a clinical fine-tune of Scribe v2.

Speech-to-text is Speechmatics' primary focus, and has been for well over a decade. ElevenLabs is a text-to-speech company that recently expanded into speech-to-text. If STT accuracy, reliability, and depth matter to your product roadmap, Speechmatics is the specialist partner built for it.

Speechmatics starts from $0.12/hr (~$0.002/min) for Melia batch transcription — all-inclusive, with no separate charges for speaker diarization or custom vocabulary. ElevenLabs Scribe v2 is $0.22/hr (~$0.0037/min) for batch; Scribe v2 Realtime is $0.39/hr (~$0.0065/min) list, or from $0.28/hr on annual Business plans. Keyterm prompting (+$0.05/hr batch, +$0.08/hr real-time) and transcript editing are billed on top.

Melia is Speechmatics’ new multilingual speech-to-text model with native code-switching across all 55+ supported languages in a single pass — no per-language model selection needed. It outperforms Deepgram, Microsoft, and AssemblyAI on most FLEURS language benchmarks, which makes it a strong fit for multilingual content, accented speakers, and global deployments. Priced from $0.12/hr for batch, it’s also the most affordable model in the Speechmatics range, and new accounts get $100 in credit to get started.

If you use ElevenLabs for text-to-speech but need production speech-to-text, look at a specialist STT API. Speechmatics, Deepgram and AssemblyAI are common alternatives. Speechmatics adds real-time speaker diarization and generally available, CPU-capable on-premises deployment. See also Speechmatics vs Deepgram.