CallMissed
Back to all models
Text to Speechspanishlow-latencyvoice-agents

Aura 2 Spanish

by Deepgram · Released 2025

Deepgram Aura 2 Spanish — 10 native Spanish voices for low-latency voice applications. Streaming MP3 output, same low-latency design as Aura 2 English.

Text to Speech

Aura 2 Spanish

Powered by Deepgram · Proprietary low-latency neural TTS

Context Window

N/A

Parameters

Undisclosed

Max Output

N/A

Category

Text to Speech

Overview

Aura 2 Spanish brings the same production-grade conversational TTS quality as Aura 2 English to Spanish-speaking markets. It offers 10 native Spanish voices spanning Latin American and Iberian styles: aquila (default), sirio, nestor, carina, celeste, alvaro, diana, selena, estrella, javier.

Deployed via Cloudflare Workers AI, it returns streaming MP3 audio just like the English variant — making it a drop-in replacement when localizing voice agents or IVR systems for Spanish-speaking customers. Pair it with Whisper Large v3 Turbo (which natively transcribes Spanish) for end-to-end Spanish voice workflows.

At $0.40 per 10K characters, pricing matches the English variant.

Pricing

MetricPrice
Price /10K chars₹40.0000

1 credit = ₹1 = $0.01 USD. Prices shown from provider; CallMissed passes through with ~35% markup.

Key Highlights

  • 10 native Spanish voices
  • Streaming MP3 output
  • Latin American + Iberian Spanish coverage
  • Same latency / encoding flexibility as Aura 2 English

Benchmarks

BenchmarkScore
Voices10
Latency~200ms
Cost$0.40

Technical Details

  • Runs on Cloudflare Workers AI (`@cf/deepgram/aura-2-es`)
  • Returns ReadableStream of MP3 audio
  • Voices: sirio, nestor, carina, celeste, alvaro, diana, aquila (default), selena, estrella, javier
  • Encoding options: mp3 (default), opus, linear16, mulaw, alaw, flac, aac

Strengths

  • 10 native Spanish voices — largest selection on the platform
  • Same low-latency streaming as Aura 2 English
  • Drop-in replacement when localizing for Spanish markets

Limitations

  • Spanish only
  • No voice cloning
  • No SSML support

Use Cases

Spanish voice agentsLATAM IVRSpanish audiobooksBilingual customer support

API Example

curl https://api.callmissed.com/v1/audio/speech \
  -H "Authorization: Bearer cm_YOUR_KEY" \
  -d '{"model": "aura-2-es", "input": "Hola, ¿en qué puedo ayudarte?", "voice": "aquila"}' \
  --output speech.mp3

Endpoint: POST /v1/audio/speech · Model ID: aura-2-es

Try Aura 2 Spanish now

Get 1000 free API credits on signup. No credit card required.

Start free Read docs