Chanty
Chanty's feed is an HR statistics content mill, not a product changelog
Comparison · Comms
Speechmatics vs Stalwart
A side-by-side editorial comparison of Speechmatics and Stalwart — release velocity, themes, recent moves, and the top alternatives to consider.
Speechmatics vs Stalwart: at a glance
| Feature | Speechmatics | Stalwart |
|---|---|---|
| Sector | Comms | Comms |
| Velocity score | 5.0 | 5.0 |
| Sparks · 30d | 0 | 0 |
| Top themes | speech-to-text, voice agents, multilingual, medical | mail-server, jmap, imap, rfc-compliance |
| Last editorial update | 3mo ago | 20h ago |
| Website | — | Visit → |
What is Speechmatics?
Speechmatics rolls its Enhanced English model across the stack, citing 89% WER gains on spellouts.
Speechmatics is a speech-recognition platform whose last quarter has been a coordinated rollout of its Enhanced Operating Point English model from containers through realtime and batch SaaS. The accuracy story is unusually concrete: 69% relative WER improvement on numbers, 89% on spellouts, 42% on mixed alphanumerics. Alongside the model work, the platform is adding voice-agent ergonomics — End of Utterance detection, prefer_current_speaker, speaker sensitivity — and broadening bilingual coverage.
What is Stalwart?
Stalwart is chasing mail RFCs and its own storage layer at the same time
Stalwart ships roughly weekly, and the releases divide cleanly between standards implementation and correctness work. v0.16.18 turns toward resource control — bounds on decompressed inbound DMARC and TLS report size, a cap on RocksDB block-cache memory, column families tuned per access pattern, and a queue scheduler that stops rescanning from the earliest pending event. The preceding releases added IMAP UIDONLY, UIDBATCHES and MESSAGELIMIT, plus JMAP email push and VAPID.
Speechmatics vs Stalwart: editorial side-by-side
Speechmatics
5.0COMMS
Speechmatics rolls its Enhanced English model across the stack, citing 89% WER gains on spellouts.
◆ Current state
Speechmatics is a speech-recognition platform whose last quarter has been a coordinated rollout of its Enhanced Operating Point English model from containers through realtime and batch SaaS. The accuracy story is unusually concrete: 69% relative WER improvement on numbers, 89% on spellouts, 42% on mixed alphanumerics. Alongside the model work, the platform is adding voice-agent ergonomics — End of Utterance detection, prefer_current_speaker, speaker sensitivity — and broadening bilingual coverage.
◆ Where it's heading
Two threads are running in parallel. Vertical depth: domain-specific models starting with medical, plus a growing list of bilingual code-switching pairs (Tagalog, Malay/English, Tamil/English, Mandarin/English, Arabic/English). Horizontal coverage: each model lands in containers first, then realtime SaaS, then batch SaaS, then appliance — containers function as the proving ground and SaaS as the broad rollout vehicle. The release notes also hint at voice agents being the primary use case Speechmatics is optimising for.
◆ Prediction
Expect more vertical-domain Enhanced models beyond medical (legal and finance are the obvious next targets) and a tighter packaging of the voice-agent primitives — End of Utterance, current-speaker locking, low-latency operating points — into something explicitly marketed as a voice-agent SDK or recipe.
Stalwart
5.0COMMS
Stalwart is chasing mail RFCs and its own storage layer at the same time
◆ Current state
Stalwart ships roughly weekly, and the releases divide cleanly between standards implementation and correctness work. v0.16.18 turns toward resource control — bounds on decompressed inbound DMARC and TLS report size, a cap on RocksDB block-cache memory, column families tuned per access pattern, and a queue scheduler that stops rescanning from the earliest pending event. The preceding releases added IMAP UIDONLY, UIDBATCHES and MESSAGELIMIT, plus JMAP email push and VAPID.
◆ Where it's heading
Two threads run through every release. One is RFC coverage across IMAP, JMAP, CalDAV and WebDAV, implemented close to the specification including drafts. The other is a long tail of protocol-conformance fixes, many of them cases where JMAP and IMAP disagreed about the same state. The newest release adds a third: memory and scheduling limits, which is what a server codebase starts doing when deployments get large enough for defaults to hurt.
◆ Prediction
Expect continued RFC additions across the JMAP and IMAP surfaces, with more of the storage-tuning work that v0.16.18 started as RocksDB deployments scale.
Alternatives to Speechmatics and Stalwart
Other Comms products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either Speechmatics or Stalwart.
Proton Bridge
Proton Bridge spends its first release in ten weeks on crashes, memory bounds and dead code
Mux
Every manual control Mux ships now arrives with a Robots workflow that does it for you
Netcore Cloud
Netcore's feed remains a demand-generation channel; ten entries, zero product releases.
mailcow
mailcow's release notes are almost entirely upstream security currency.
Openfire
Openfire keeps its XMPP server current without changing what it is.
See all Speechmatics alternatives → · See all Stalwart alternatives →
Recent activity from Speechmatics and Stalwart
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 1d agoStalwartResource limits arrive for inbound reports and RocksDB caches
- 8d agoStalwartIMAP gains UIDONLY, UIDBATCHES and message-limit extensions
- 16d agoStalwartJMAP delivery push arrives; strict relays stop rejecting calendar mail
- 23d agoStalwartFix-only release: JMAP semantics and a credential escalation
- 29d agoStalwartVAPID lands for JMAP Web Push
- 1mo agoStalwartFreeBSD support, plus OAuth scopes for IMAP, SMTP and Sieve
- 3mo agoSpeechmatics15.7.0 - Containers ⚡
- 3mo agoSpeechmatics2026.04.23 Realtime SaaS
- 4mo agoSpeechmatics2026.04.16 Batch SaaS
- 5mo agoSpeechmatics2026.03.12 - Realtime SaaS
- 5mo agoSpeechmatics2026.03.09 - Batch SaaS
- 5mo agoSpeechmatics1.2.0 Realtime Kubernetes — Redis repopulation and CVE patches
Frequently asked questions
What is the difference between Speechmatics and Stalwart?
They serve adjacent needs but don't currently overlap on shipped themes. Speechmatics and Stalwart are shipping at a similar cadence (velocity 5.0 vs 5.0, both within Sparkpulse's "active" band). See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Is Speechmatics better than Stalwart?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. Speechmatics and Stalwart are shipping at a similar cadence (velocity 5.0 vs 5.0, both within Sparkpulse's "active" band). For your specific use case, the alternatives sections above list other Comms products to evaluate alongside.
What are the best alternatives to Speechmatics?
Top Speechmatics alternatives in Comms are ranked by recent ship velocity. Browse the "Speechmatics alternatives" section above for the current picks, or visit /alternatives/speechmatics for the full list with editorial commentary on each.
What are the best alternatives to Stalwart?
Top Stalwart alternatives in Comms are ranked by recent ship velocity. Browse the "Stalwart alternatives" section above for the current picks, or visit /alternatives/stalwart for the full list with editorial commentary on each.