← All providers
Docs·API
Deepgram

Deepgram

SpeechFREE TIER

STT, TTS, audio intelligence — production-grade ASR

deepgram.com ↗Pricing →/api/v1/latency

Operational

All systems responding normally

Last checked 10/06/2026, 1:46:52 pm

285ms response

Uptime History99.33% uptime
2026-06-04Today

Uptime

99.33%

Avg Latency

292ms

P95 Latency

404ms

Fastest

62ms

Checks

150

Response Time

Last 60 checks
62ms min292ms avg2730ms max

💰 Pricing

nova-3FREE
STT: $0.0043/min

TTS: $0.015/1k chars. Batch STT: $0.0025/min

$200 credit free

⚡ Rate Limits

free
Concurrent: 5

$200 free credit. 5 concurrent streams.

🤖 Models (1)

ModelTaskContextVisionToolsJSON
Nova-3

Advanced STT + TTS. Real-time transcription.

speech————

Recent Checks

Showing last 15
Operational
285ms10 June, 01:46 pm
Operational
279ms10 June, 12:22 pm
Operational
180ms10 June, 11:20 am
Operational
200ms10 June, 10:04 am
Operational
214ms10 June, 09:31 am
Operational
220ms10 June, 08:52 am
Operational
277ms10 June, 08:13 am
Operational
304ms10 June, 07:36 am
Operational
347ms10 June, 06:51 am
Operational
248ms10 June, 06:05 am
Operational
240ms10 June, 05:17 am
Operational
210ms10 June, 04:22 am
Operational
264ms10 June, 03:32 am
Operational
424ms10 June, 02:42 am
Operational
350ms10 June, 01:42 am

API Quick Access

HealthLatencyFreshnessPricingModels

Other Speech Providers

ElevenLabs

ElevenLabs

TTS, voice cloning, STT — most realistic speech AI

AssemblyAI

AssemblyAI

Transcription + speaker diarization + LeMUR

Cartesia

Cartesia

Ultra-low latency TTS — real-time voice for agents

Visit Deepgram →View Pricing← All Providers