# Deepgram Text-to-Speech (Aura-2, Flux TTS) (slim)

> Deepgram's text-to-speech API for generating spoken audio.

- Full: https://www.anchorterminal.com/tools/deepgram-tts.md (~6,150 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/deepgram-tts.json · canonical https://www.anchorterminal.com/tools/deepgram-tts
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**BB · 73/100 · rank #63 of 452 · #4 in Text-to-speech · agent-ready · confidence high**


Assessment: OpenAPI 3.1 and AsyncAPI files, llms.txt and Markdown pages. Requests can be kept for training unless each one sets `mip_opt_out=true`.

## Facts

- Kind: Model API · vendor: Deepgram · category: Text-to-speech · legal entity: Deepgram, Inc. · provenance 90/100
- Endpoint: `https://api.deepgram.com/v1` (HTTP, Streamable HTTP, stdio, SSE (legacy))
- Auth: API key · pricing: Pay per use · x402: no · licence: MIT (SDKs)
- Probe metrics: not measured yet (probes haven't run)
- Models: Flux TTS (`flux-{voice}-en`) on `/v2/speak`, Aura-2 (`aura-2-{voice}-{lang}`) and Aura-1 (`aura-{voice}-en`) on `/v1/speak`
- Voices: 36 Flux TTS voices, about 90 Aura-2 voices, 12 Aura-1 voices
- Languages: Flux TTS English with 7 accents. Aura-2 English, Spanish, German, French, Dutch, Italian and Japanese, with English and Spanish code-switching on 5 Spanish voices
- Time to first audio: No figure published in the docs
- SSML: Not supported. Aura-2 has speed and IPA pronunciation controls. Flux TTS has speed and a beta expressivity dial
- Long-form: Aura-2 REST caps at 2,000 characters a request. Flux TTS streaming sessions close after 1 hour or 60 seconds idle
- Output: Streaming PCM, mu-law or A-law at 8 to 48 kHz. Batch adds MP3, Opus, FLAC and AAC
- Free tier: $200 one-off credit, no card
- Rate limits: REST 15 concurrent requests, streaming 45 in North America. Flux TTS is 5 in the EU, Australia and India
- Data retention: Covered by the Model Improvement Program. Opt out per request with `mip_opt_out=true`
- Custom voices: Enterprise only, through sales
- Prices: Flux TTS $45 per 1M characters; Aura-2 $30 per 1M characters; Aura-1 $15 per 1M characters; Aura-2 on Growth $27 per 1M characters

- Scores: Reliability 70, Performance pending, Schema & documentation 95, Agent ergonomics 82, Security & auth 70, Payments & pricing 40, Task success pending, Maintenance & community 73, Transparency & trust 75 · total over the 7 assessed categories
- Why: Reliability, Statuspage at status.deepgram.com with component history and an RSS feed back to May 2026 (20). · Schema & documentation, OpenAPI 3.1 file at developers.deepgram.com/openapi.json and an AsyncAPI file for the sockets (25). · Agent ergonomics, API reading of the checklist. · Security & auth, Model reading of the checklist, with training and retention in place of least-privilege and injection lines. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Read as a model. · Transparency & trust, Closed service with clear terms, SDKs MIT (15).
- Sources: 13, open questions: 3, both in the full twin
- Capabilities: speech.tts, speech.streaming, speech.voices, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/deepgram-tts.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/deepgram-tts.svg` or a link to https://www.anchorterminal.com/tools/deepgram-tts from a page on deepgram.com or one of its subdomains, or the README of github.com/deepgram/deepgram-python-sdk, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Set `mip_opt_out=true` on every request if the text mustn't be kept for training.
2. Split Aura-2 REST text under 2,000 characters or expect a 413.
3. Pass `model` on `/v2/speak`, where it's required.
4. Strip SSML before sending, since it's removed with an `INPUT_MARKUP_STRIPPED` warning.
5. Back off exponentially on 429 and keep traffic in one project.

## Connect

```bash
curl "https://api.deepgram.com/v1/speak?model=aura-2-thalia-en" \
  -H "Authorization: Token $DEEPGRAM_API_KEY" -H "content-type: application/json" \
  -d '{"text":"Hello, how are you?"}' -o hello.mp3
```

```bash
claude mcp add deepgram-docs --transport http https://api.dx.deepgram.com/kapa/mcp
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Amazon Polly | BB | 75.8 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/amazon-polly.min.md |
| Azure AI Speech text-to-speech | BB | 73.7 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/azure-text-to-speech.min.md |
| ElevenLabs Text to Speech API + MCP | BB | 73.1 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/elevenlabs-tts.min.md |
| Murf TTS API + MCP | BB | 70.9 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/murf-tts.min.md |
| Cartesia Sonic TTS API + MCP | B | 64.2 | speech.tts, speech.streaming, speech.voices, speech.languages | https://www.anchorterminal.com/tools/cartesia-tts.min.md |


## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made)

- ★★★★☆ $30 per 1M characters and $200 of credit without a card (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★☆☆ Four hours of Flux TTS errors and no SLA document (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)