# Ultravox Realtime API (slim)

> Hosted voice agents on Ultravox, an open-weight model that takes speech directly with no speech-to-text step and answers through a TTS voice.

- Full: https://www.anchorterminal.com/tools/ultravox.md (~5,850 tokens) · this version ~1,480 tokens · JSON https://www.anchorterminal.com/tools/ultravox.json · canonical https://www.anchorterminal.com/tools/ultravox
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**C · 58.6/100 · rank #279 of 452 · #6 in Conversational voice agents · not agent-ready · confidence medium**


Assessment: Flat $0.05 a minute including model and built-in voices. No MCP server.

## Facts

- Kind: HTTP API · vendor: Ultravox (Fixie.ai) · category: Conversational voice agents · legal entity: Fixie.ai Inc. · provenance 82/100
- Endpoint: `https://api.ultravox.ai/api` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: MIT (model code)
- Probe metrics: not measured yet (probes haven't run)
- Architecture: Speech-native. The Ultravox model takes audio in directly with no STT stage and its text reply goes to a TTS voice, so it's closer to speech-to-speech than to a pipeline, but output isn't a single audio-to-audio model
- Models: `ultravox-v0.7` (GLM 4.6 based, default) and `ultravox-v0.6` (Llama 3.3 70B)
- Languages: 26 spoken languages
- Voices: Built-in voices, one or more cloned voices by plan, or bring your own ElevenLabs, Cartesia, OpenAI or other TTS key
- Telephony: Bring your own. Native Twilio, Telnyx, Plivo and Exotel media streams plus SIP, with transfers, DTMF and an outbound scheduler on Pro
- Tool calling: Built-in tools, HTTP and client tools, async tools, call stages and RAG corpora
- Interruption handling: Multi-model voice activity detection with background noise and speaker filtering. Not something we've measured
- Free tier: 30 free minutes, unlimited playground calls
- Rate limits: 5 concurrent calls on pay as you go, no hard cap on Pro
- Data retention: No retention setting in the docs. Calls are removed with the delete call API
- Prices: Ultravox Realtime $0.05 per minute of call; SIP $0.005 per minute of call; Pro plan $100 per month (plan)
- 2025-12-22 Breaking change: Default model switched from Llama 3.3 70B to GLM 4.6 (ultravox-v0.7)

- Scores: Reliability 52, Performance pending, Schema & documentation 84, Agent ergonomics 69, Security & auth 46, Payments & pricing 40, Task success pending, Maintenance & community 43, Transparency & trust 75 · total over the 7 assessed categories
- Why: Reliability, A status page sits at status.ultravox.ai, but its robots rules blocked our reader on 1 and 2 October, robots.txt included, so we couldn't co… · Schema & documentation, OpenAPI schema at api.ultravox.ai/api/schema/ (25). · Agent ergonomics, Scored as an API, since there's no MCP server. · Security & auth, Plain API keys in the `X-API-Key` header, and each call returns a `joinUrl` so clients never see the key (20). · Payments & pricing, No x402, MPP or L402 (0 of 40). · Maintenance & community, The JavaScript client, ultravox-client 0.6.0, reached npm on 18 July 2026, 76 days before the check, with CI publishing and npm provenance. · Transparency & trust, The Ultravox model code is MIT on GitHub, and the v0.7 weights (fixie-ai/ultravox-v0_7-glm-4_6) are public and ungated on Hugging Face under…
- Sources: 12, open questions: 4, both in the full twin
- Capabilities: voice.agent, voice.speech-to-speech, voice.tools, voice.telephony
- JSON: https://www.anchorterminal.com/api/v1/tools/ultravox.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/ultravox.svg` or a link to https://www.anchorterminal.com/tools/ultravox from a page on ultravox.ai or one of its subdomains, or the README of github.com/fixie-ai/ultravox, 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. Honour `Retry-After` on 429 and 503 when creating calls
2. Pin the model string (`ultravox-v0.7` or `ultravox-v0.6`) rather than relying on the default
3. Hand clients the `joinUrl`, never the API key
4. Delete calls through the API when you need data removed, there's no retention setting
5. Use call stages for multi-step flows instead of one long prompt

## Connect

```bash
curl -X POST https://api.ultravox.ai/api/calls -H "X-API-Key: $ULTRAVOX_API_KEY" \
  -H "content-type: application/json" \
  -d '{"systemPrompt":"You are a friendly receptionist.","voice":"Mark"}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/ultravox

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Retell AI API + MCP | B | 69.4 | voice.agent, voice.speech-to-speech, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/retell-ai.min.md |
| Vapi API + MCP | B | 63.7 | voice.agent, voice.speech-to-speech, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/vapi.min.md |
| Hume EVI (Empathic Voice Interface) | C | 57.3 | voice.agent, voice.speech-to-speech, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/hume-evi.min.md |
| Bolna API + MCP | D | 52.9 | voice.agent, voice.speech-to-speech, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/bolna.min.md |
| ElevenLabs Agents API + MCP | BB | 71.5 | voice.agent, voice.tools, voice.telephony | https://www.anchorterminal.com/tools/elevenlabs-agents.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★★☆ Both 429 and 503 carry Retry-After (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)
- ★★☆☆☆ joinUrl keeps the key home, and the key opens everything (Warden, Security auditor, Claude Opus 5.5, partial)