Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Sarvam Bulbul v3 Sarvam AI | Resemble AI TTS (Chatterbox models) Resemble AI | Neuphonic API Neuphonic | |
|---|---|---|---|
| Category | Text-to-speech | Text-to-speech | Text-to-speech |
| Status | Beta | GA | GA |
| Est. per minute | n/a | n/a | n/a |
| How that was worked out | Priced in INR (about INR 2.7/min at 900 chars for v3); USD not computed to avoid an assumed FX rate | Not verifiable from official pages; third-party sources range from ~$0.03 to ~$0.36 per minute | Pricing not published |
| Pricing model | per-character | per-minute | subscription |
| Free tier | INR 1,000 free credits on every new plan | Flex pay-as-you-go credits never expire (detection page); TTS free tier not verified | Playground available; API free tier not verified |
| Connects by | WebSocket, HTTP chunked | WebSocket, HTTP chunked | WebSocket, SSE |
| Audio in | Text | Text or SSML, max 3,000 characters excluding tags | Text with inline <pause> and <phoneme> tags |
| Audio out | Default 24,000 Hz; formats not verified | wav/pcm etc.; example uses wav 32 kHz PCM_32; JSON (base64) or binary frames | Not verified |
| Languages | Indian languages (e.g. hi-IN) plus English; exact list not verified | English for Turbo; Chatterbox Multilingual covers 23+ languages | 37 (homepage playground); NeuTTS-2M spec lists 7 |
| Latency (vendor claim) | Not verified | Vendor (Chatterbox README): hosted service sub-200 ms. | Third-party listings cite a vendor sub-25 ms figure; Vapi Humanness Index measured ~763 ms for the model it tested. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Not verified. | Enterprise on-prem available; SOC 2 documentation mentioned for enterprise on the pricing page. | Not verified. |
| Self-hostable | No | Yes | Yes |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/1M chars | - | - | - |
| Free tier | Yes | - | - |
| Free credit $ | - | - | - |
| Free tier commercial | - | - | - |
| Voices | - | - | - |
| Cloning | - | Yes | Yes |
| Instant clone | - | - | - |
| Text stream in | Yes | No | - |
| Timestamps | - | Yes | - |
| Emotion | - | - | - |
| SSML | - | Yes | - |
| 8 kHz phone | - | - | - |
| Latency ms | - | 200 | 25 |
| Languages | - | 1 | 37 |
| Max session min | - | - | - |
| Concurrency | - | 20 | - |
| WebRTC | No | No | No |
| WebSocket | Yes | Yes | Yes |
| gRPC | No | No | No |
| HIPAA | - | - | - |
| SOC 2 | - | Yes | - |
| EU data | No | - | - |
| Self-host | No | Yes | Yes |
| Open weights | No | Yes | Yes |
| High warnings | 0 | 2 | 0 |