Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Groq TTS (Canopy Labs Orpheus) Groq | Deepgram Aura-2 Deepgram | Amazon Polly (generative and bidirectional streaming) Amazon Web Services | |
|---|---|---|---|
| Category | Text-to-speech | Text-to-speech | Text-to-speech |
| Status | GA | GA | GA |
| Est. per minute | $0.02 - 0.036 | $0.024 - 0.027 | $0.014 - 0.027 |
| How that was worked out | 900 chars/min; English vs Arabic | 900 chars/min; Aura-2 Growth vs PAYG | 900 chars/min. Bidi streaming requires generative ($30/1M = $0.027); neural $16/1M = $0.0144 without input streaming. |
| Pricing model | per-character | per-character | per-character |
| Free tier | Groq free tier rate limits apply (not re-verified for TTS) | $200 credit for new accounts | 12 months: 5M standard, 1M neural, 500K long-form, 100K generative characters per month; new accounts also get up to $200 AWS credits |
| Connects by | HTTP chunked | WebSocket, HTTP chunked | HTTP chunked, HTTP/2 bidirectional event stream |
| Audio in | Text, max 200 characters, with [directions] | Plain text | Plain text or SSML |
| Audio out | wav only | 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. | mp3, ogg_opus, ogg_vorbis, pcm (stream API; JSON speech marks not supported on the stream API) |
| Languages | English; Arabic (Saudi) | 7 for Aura-2: en, es, nl, fr, de, it, ja (changelog Dec 2025 / Jan 2026) | Stream API LanguageCode list covers ~40 locales (only needed for bilingual voices) |
| Latency (vendor claim) | No numeric claim on Groq's page. | Vendor claim: sub-200 ms (Aura-2 product page). No figure on the streaming docs page. | No numeric claim found. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Not verified. | Self-hosted deployment available (Deepgram docs). Certifications not re-verified here. | AWS compliance programs (GovCloud availability for standard/neural). |
| Self-hostable | No | Yes | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/1M chars | $22 | $30 | $30 |
| Free tier | Yes | Yes | Yes |
| Free credit $ | - | $200 | $200 |
| Free tier commercial | - | - | - |
| Voices | 6 | - | - |
| Cloning | - | - | No |
| Instant clone | - | - | No |
| Text stream in | No | Yes | Yes |
| Timestamps | - | - | Yes |
| Emotion | Yes | - | - |
| SSML | - | - | Yes |
| 8 kHz phone | No | Yes | No |
| Latency ms | - | 200 | - |
| Languages | 2 | 7 | - |
| Max session min | - | 60 | - |
| Concurrency | - | 45 | - |
| WebRTC | No | No | No |
| WebSocket | No | Yes | No |
| gRPC | No | No | No |
| HIPAA | - | Yes | - |
| SOC 2 | - | Yes | - |
| EU data | - | - | Yes |
| Self-host | No | Yes | No |
| Open weights | No | No | No |
| High warnings | 2 | 1 | 1 |