Capabilities
Explore what Aura 2 supports, then use the API section for a request tailored to this model.
Languages
Model Information
- Provider
- Deepgram
- Product
- Text-to-Speech
- Release Date
- Apr 15, 2025
- Data Policy
- Configurable
- Region
- Unknown
- Input
- Text
- Output
- Audio
Playground
Try Aura 2 by Deepgram. Requests use the selected workspace’s credits and API pricing.
Providers
Compare available endpoints, pricing, and context limits for Aura 2.
| Provider | Context | Output | Input Price | Output Price | Endpoint |
|---|---|---|---|---|---|
| Deepgram | Not specified | Audio | $25.50 / 1M characters | — | deepgram/aura-2:deepgram |
Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, opus, aac, flac, wav, pcm, ulaw, alaw |
Provider Notes
deepgram/realtime is AudioLab's provider-managed Nova-3 + GPT-4o Mini + Aura-2 Thalia speech-to-speech stack. Aura-2 supports every current REST media combination, streaming HTTP audio, asynchronous callbacks, request tags, MIP opt-out, speed and inline IPA controls, and AudioLab's realtime speech WebSocket. It has 91 current voice/model IDs across seven languages. Aura-1 remains an officially listed, separately priced English model family with 12 voice/model IDs and the same REST/WebSocket transports, but without Aura-2's speed or inline IPA controls. Pass the provider's full concrete voice/model ID, such as aura-2-thalia-en, through the common voice field. MP3, Opus, and AAC use Deepgram's fixed sample rates, so AudioLab omits sample_rate for those encodings; configurable sample rates remain available for linear16, mu-law, A-law, and FLAC. Deepgram's live WebSocket accepts only pcm, ulaw, or alaw.
Performance
Status
Current catalog availability. Your workspace’s access is checked separately before a request runs.
A live availability check is not available right now.
Getting Started
Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.
curl "$AUDIOLAB_API_URL/v1/audio/speech" \
-H "Authorization: Bearer $AUDIOLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepgram/aura-2",
"input": "Make every word count.",
"voice": "auto",
"response_format": "mp3"
}' --output speech.mp3Request Parameters
Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.
| Parameter | Details |
|---|---|
model | deepgram/aura-2 — Required model identifier. |
encoding | View Accepted Values |
container | View Accepted Values |
sample_rate | View Accepted Values |
bit_rate | View Accepted Values |
mip_opt_out | View Accepted Values |
tag | View Accepted Values |
callback | View Accepted Values |
callback_method | View Accepted Values |
Input and Output Limits
Formats and limits AudioLab enforces on each request.
| Limit | Value |
|---|---|
| Max chars | 2000 |
| Formats | mp3, opus, aac, flac, wav, pcm, ulaw, alaw |
Similar Models
Explore more text-to-speech and compare their capabilities.
| Model | Context | Input Price | Output Price |
|---|---|---|---|
| Aura 1Deepgram | Not specified | $12.75 / 1M characters | — |
| Sonic 3.6Cartesia | Not specified | $38.25 / 1M characters | — |
| Sonic 3.6 (2026-08-27)Cartesia | Not specified | $38.25 / 1M characters | — |
| tts-rt-v2Soniox | Not specified | $11.985 / 1M characters | — |
| Inworld TTS-2 FlashInworld AI | Not specified | $12.75 / 1M characters | — |
| audio8DeepInfra | Not specified | $4.25 / 1M characters | — |
