Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Deepgram Aura-2 Deepgram | Rime TTS (Coda, Mist v3) Rime Labs | Groq TTS (Canopy Labs Orpheus) Groq | |
|---|---|---|---|
| Category | Text-to-speech | Text-to-speech | Text-to-speech |
| Status | GA | GA | GA |
| Est. per minute | $0.024 - 0.027 | $0.027 - 0.045 | $0.02 - 0.036 |
| How that was worked out | 900 chars/min; Aura-2 Growth vs PAYG | 900 chars/min; Mist v3 vs Coda at Starter rates | 900 chars/min; English vs Arabic |
| Pricing model | per-character | per-character | per-character |
| Free tier | $200 credit for new accounts | Page conflicts: '~800 minutes free (about 800k characters)' vs FAQ '3,000 free minutes' | Groq free tier rate limits apply (not re-verified for TTS) |
| Connects by | WebSocket, HTTP chunked | WebSocket, HTTP chunked | HTTP chunked |
| Audio in | Plain text | Text (custom pronunciation via spell() and dictionaries) | Text, max 200 characters, with [directions] |
| Audio out | WebSocket: linear16, mulaw, alaw (container none); linear16 8/16/24/32/48 kHz, mulaw/alaw 8 or 16 kHz. REST adds mp3 (22.05 kHz), opus (48 kHz ogg), flac, aac. | pcm, mp3, mulaw (audioFormat); sample rates per model reference | wav only |
| Languages | 7 for Aura-2: en, es, nl, fr, de, it, ja (changelog Dec 2025 / Jan 2026) | Coda: 8; Mist v3: 4 | English; Arabic (Saudi) |
| Latency (vendor claim) | Vendor claim: sub-200 ms (Aura-2 product page). No figure on the streaming docs page. | Vendor: sub-200 ms end-to-end via cloud API; Mist v3 typical TTFB well below 100 ms; Coda sub-100 ms model latency on GPU engine (self-hosted) plus 25-50 ms network from most of the US. | No numeric claim on Groq's page. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Self-hosted deployment available (Deepgram docs). Certifications not re-verified here. | Enterprise: BAA and SOC 2 reports; optional request-data retention controls (disabled by default). | Not verified. |
| Self-hostable | Yes | Yes | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/1M chars | $30 | $50 | $22 |
| Free tier | Yes | Yes | Yes |
| Free credit $ | $200 | - | - |
| Free tier commercial | - | - | - |
| Voices | - | - | 6 |
| Cloning | - | - | - |
| Instant clone | - | - | - |
| Text stream in | Yes | Yes | No |
| Timestamps | - | Yes | - |
| Emotion | - | - | Yes |
| SSML | - | - | - |
| 8 kHz phone | Yes | Yes | No |
| Latency ms | 200 | 200 | - |
| Languages | 7 | 8 | 2 |
| Max session min | 60 | - | - |
| Concurrency | 45 | 20 | - |
| WebRTC | No | No | No |
| WebSocket | Yes | Yes | No |
| gRPC | No | No | No |
| HIPAA | Yes | Yes | - |
| SOC 2 | Yes | Yes | - |
| EU data | - | - | - |
| Self-host | Yes | Yes | No |
| Open weights | No | No | No |
| High warnings | 1 | 1 | 2 |