Speechmatics

Founded in 2006 by Dr. Tony Robinson, a Cambridge University speech recognition pioneer, Speechmatics builds infrastructure to understand every voice globally. The company's core mission is inclusive, multilingual speech AI, covering transcription, real-time voice agents, and on-device deployment. Speechmatics serves enterprise clients across media, healthcare, financial services, and contact centers.

General
Company	Speechmatics
Founded	2006 by Dr. Tony Robinson
CEO	Katy Wigdahl
Headquarters	Cambridge, United Kingdom
Website	speechmatics.com
Documentation	docs.speechmatics.com
GitHub	github.com/speechmatics
Type	Speech AI / B2B SaaS

Core Products

Speechmatics API (Speech-to-Text)

The Speechmatics API provides batch and real-time transcription across 55+ languages, with speaker diarization, custom dictionaries, automatic translation, and Voice Intelligence add-ons (summarization, sentiment analysis, entity recognition). Three models sit behind the same API, so moving between them is a choice at request time rather than a new integration: Enhanced for highest accuracy on single-language audio (with a specialist Enhanced Medical variant for clinical use), Standard for the fastest turnaround, and Melia 1 for audio that switches between languages mid-conversation. See our Speechmatics API tech page for the full breakdown.

Voice Agents

Speechmatics powers the listening layer of real-time voice agents, providing turn detection, intelligent segmentation, diarization, speaker focus for multi-speaker scenarios, and preset configurations for a fast start. Developers can build through integration partners LiveKit, Pipecat, and Vapi for the fastest path to production, or the Voice SDK for custom pipelines.

Developer Resources

Speechmatics provides SDKs for Python, JavaScript/TypeScript, and .NET, along with a developer portal and free tier to get started without a credit card.

Helpful Links

Documentation — official API reference, quickstarts, and integration guides
GitHub — open-source SDKs and client libraries
Developer Portal — API key management and usage dashboard
Pricing — free tier and pay-as-you-go rates

Key Features

Multilingual transcription across 55+ languages Speechmatics leads accuracy benchmarks in 62% of supported languages on the FLEURS dataset, with 7.88% WER on Kincaid46 for English, surpassing human-level accuracy on that benchmark.

Flexible deployment Speechmatics runs on private SaaS cloud, on-premises, on-device, and via Docker or Kubernetes, making it suitable for data-sensitive industries like healthcare and finance.

Voice Intelligence add-ons Summarization, sentiment analysis, topic detection, chapter generation, and entity recognition layer on top of transcription without requiring additional integration work.

Use Cases

Contact center automation Real-time transcription and sentiment analysis during calls, combined with the Voice Agents building blocks for automated handling of common queries.

Clinical transcription Speechmatics' Enhanced Medical model targets 93% real-time accuracy and 96% medical keyword recall, covering English, Arabic English, Danish, Dutch, Finnish, French, German, Norwegian, Spanish, and Swedish.

Media and broadcast Batch transcription of audio and video files for subtitling, archiving, and content search across multiple languages.

Nexus

Nexus is a multi-tenant social messaging platform that unifies Telegram, WhatsApp, and LinkedIn conversations into a single, real-time inbox. Built on Next.js, MongoDB, and Socket.io, it gives support teams one place to read, reply, and manage messages across all channels — with Speechmatics-powered translation so agents can communicate in any language without leaving the thread. Role-based access, a BullMQ task queue, full-text search, canned responses, analytics dashboards, and SLA timers make Nexus a complete customer-communication layer for teams of any size.

TableSync: Dual-Arm Robotic Manipulation

TableSync is a bimanual manipulation framework for coordinated multi-arm desktop manipulation tasks in simulated physics. It enforces a strict, type-safe boundary between high-level multimodal reasoning (Gemini API emitting structured Pydantic plans) and deterministic low-level physical execution (damped least-squares inverse kinematics, waypoint generation, and contact-state verification over MuJoCo physics). TableSync decouples perception and reasoning from real-time joint control through a four-tier architecture: +-------------------------------------------------------------------------+ | Perception & Reasoning Layer | | - Multimodal camera perception (overhead camera RGB frames) | | - Task decomposition & atomic action sequencing | | - JSON-mode structured output validated against Pydantic schema | +------------------------------------+------------------------------------+ | PlannerOutput (JSON) v +-------------------------------------------------------------------------+ | Interface Boundary (`contracts.py`) | | - Enums: ArmID, ActionType, TargetObject, SubtaskStatus, HandoffPhase | | - Models: Subtask, PlannerOutput, ExecutionResult, HandoffState | | - Mutual reach waypoint: HANDOFF_POINT_WORLD = (0.0, 0.15, 0.30) | | - Safety contract: GRIP_DWELL_FRAMES = 10 consecutive contact checks | +------------------------------------+------------------------------------+ | Validated Subtask Sequence

BimanualIQ

BimanualIQ is a voice-controlled Physical AI system designed for intelligent two-arm robotic manipulation. It combines natural-language understanding, visual perception, multimodal reasoning, motion planning, and coordinated execution to let users control two robotic arms through simple spoken instructions. In the core demo, a user can say, “Set the table for two, and do not use the red cup,” and BimanualIQ interprets the request, detects objects in the scene, builds a task plan, assigns actions to each arm, and completes the table-setting workflow inside MuJoCo. The system uses Speechmatics for real-time speech recognition, camera observations for scene understanding, and a VLA-based reasoning layer for translating intent into physical actions. A bimanual coordinator decides when the arms should work independently, perform handoffs, stabilize objects, or execute synchronized movements. BimanualIQ also monitors execution continuously, allowing it to detect failed grasps, misplaced objects, unexpected disturbances, and new voice commands, then replan without restarting the entire task. OpenVINO optimizes perception and AI inference for Intel Core Ultra Series 2/3 hardware, while seeded simulation tests measure task completion, robustness, latency, and generalization across randomized environments. The result is a practical, adaptive, and reproducible platform for conversational bimanual robotics. It demonstrates how spoken intent can become physical action.

BimanualIQ

KINLOCK: Bimanual VLA Flight Envelope Protection

Vision-Language-Action (VLA) models propose actions at 10–30 Hz, while physical robot servos execute at 1,000 Hz. In bimanual tasks—such as two robot arms carrying an object together—this frequency gap causes kinematic drift between the end-effectors. Documented in Hugging Face LeRobot Issue #3154, this drift generates over 2,000 N of internal tensile and compressive force, stripping servo gears and destroying physical hardware. KINLOCK provides deterministic, sub-millisecond Flight Envelope Protection (FEP) for dual-arm robotic systems. Positioned directly between any high-level VLA model and low-level servo controllers, KINLOCK projects unconstrained velocity proposals onto the null-space of closed-chain kinematic constraints using Moore-Penrose pseudo-inversion and Baumgarte drift stabilization (α = 12.0 s⁻¹). Benchmarked against dual SO-101 6-DOF arms on a 150-frame table-setting dataset, KINLOCK reduces peak internal strain from 2,033.99 N down to 0.02 N (100% attenuation) within a 72.5 μs callback dispatch, strictly preserving the 348.24 mm grasp invariant without interrupting ongoing task execution. Additionally, KINLOCK integrates Speechmatics Realtime WebSocket API for acoustic emergency reflexes. When an operator utters "STOP" or "HALT", KINLOCK parses the phoneme stream and triggers an exponential admittance deceleration curve: bringing arm velocities to a complete halt in under 50 ms while sustaining 100% gripper clamp torque so carried objects never drop.

Intel Bimanual Robot Voice Control MVP

This project implements a full voice-to-robot pipeline for bimanual manipulation in simulation, built for the Intel Physical AI Online Challenge. ARCHITECTURE 1. Voice Input — A browser frontend captures microphone audio and streams raw 16kHz PCM over a WebSocket to a FastAPI backend. The backend proxies it to Speechmatics real-time STT, returning transcripts with low latency using the standard language model. 2. Language Understanding — Transcripts go to a local Ollama LLM (phi3:mini) running on-device. A structured prompt maps natural language to one of five task IDs: pick_place, drawer_open, drawer_close, door_open, or button_press. A keyword fallback handles cases where the model is unavailable. 3. Simulation — Tasks run in MetaWorld (MuJoCo-backed), a standard robotic manipulation benchmark. Each environment has a 4-DOF action space and a 480x480 RGB camera. A live OpenCV window shows the robot camera view as the task executes. 4. Intel Optimization — A ResNet18 vision encoder is exported to OpenVINO IR and benchmarked on Intel hardware. CPU: 10.1 FPS (98.9ms). Intel iGPU: 15.2 FPS (65.7ms). That is a 1.5x speedup from OpenVINO hardware-aware inference. RESULTS 100% task success across all five tasks, evaluated over 10 random seeds each. Average episode: 52 steps, 3.3 seconds. Voice-to-motion latency under 1 second. SUPPORTED TASKS pick_place, drawer_open, drawer_close, door_open, button_press INTEL TECHNOLOGIES OpenVINO converts and runs the vision encoder on Intel CPU and iGPU. The pipeline targets Intel Core Ultra Series 2/3 hardware with NPU support in the benchmark runner. All inference is local — no cloud GPU required.