Review · Software & AI
Speechmatics review
A UK speech-to-text API with multilingual, medical and voice agent models that runs in the cloud, on-prem or on-device.
By the DBotMaker research desk · Updated November 7, 2026
- Capabilities (40%)
- 8.8
- Ease of setup (30%)
- 8.4
- Value (30%)
- 9.2
Speechmatics prices each model separately and publishes every rate. For pre-recorded audio, Melia 1 costs $0.12 per hour and transcribes 56 languages without being told which one to expect, switching mid-sentence when speakers do. The Enhanced model costs $0.38 per hour, adds a custom dictionary and is the vendor's most accurate option, and Oak 1 handles clinical language for $0.15 per hour in batch. For live audio, Linden 1 is built for voice agents with turn detection at $0.15 per hour, and Melia 1 real-time costs $0.20. Speechmatics says real-time transcripts arrive in under one second. New accounts get $100 in credits with no card, credit packs start at $25, and volume discounts reach 25%. The company also lists on-prem and on-device deployment, which few rivals offer at this price. Add-ons such as translation at $0.49 per hour and chapters at $0.30 add up quickly.
Who it is for
Teams with mixed-language audio or large batch volumes who want the lowest published hourly rate.
Price
Free start with $100 in credits and no card; pre-recorded from $0.12 per hour (about $0.002 per minute) on Melia 1; real-time from $0.15 per hour on Linden 1.
World class speech to text from $0.12/hr
Quoted from the vendor pricing page on November 7, 2026.
Key features
- Melia 1 transcribes 56 languages without choosing one first and handles mid-sentence switches
- Enhanced model with custom dictionary and advanced punctuation
- Linden 1 voice agent model with built-in turn detection
- Oak 1 medical model for drug names, dosages and clinical terms
- Speaker diarization, translation, summaries and sentiment as add-ons
Strengths and weaknesses
- Strength: Lowest published batch rate in this list at $0.12 per hour
- Strength: $100 starting credit with no card
- Strength: Cloud, on-prem and on-device deployment
- Weakness: Enhanced accuracy costs $0.38 per hour for batch and $0.40 for real-time
- Weakness: Real-time latency is described as under one second, not a tighter figure
- Weakness: Translation and chapters cost extra per hour
Key facts
- Free credit: $100, no card required
- Languages: 55+
- Discounts: Up to 25% volume discount, 33% opt-in training discount
Where it ranks
Speechmatics is No. 3 in our Best Speech-to-Text APIs verdict.
Alternatives we scored
- AssemblyAI9.1
- Deepgram9.0
- ElevenLabs Scribe8.7
- Gladia8.5
Visit speechmatics.com · Questions or corrections: editorial@dbotmaker.io