Sonic 3.6
Sonic 3.6 is Deepgram's text to speech model. A real-time TTS model from Cartesia offering low-latency, high-quality speech synthesis for streaming voice applications.
| Specifications | |
|---|---|
deepgram-sonic-3-6 | |
| Text to Speech | |
| Active | |
| Deepgram | |
| Text | |
| Audio | |
| Benchmarks | |
|---|---|
| Elo Rating | #14 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio✓
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Sonic 3.6 | — | — | — | — | Current |
| Sonic 3 | — | — | — | — | Available |
| Sonic 3.5 | — | — | — | — | Available |
| Sonic English | — | — | — | — | Available |