Ultravox Agents
by Fixie.ai
Speech-native LLM and hosted agent runtime by Fixie.ai.
TL;DR
Speech-native LLM and hosted agent runtime by Fixie.ai.
Best for developers wanting an open speech-native LLM as the brain of their voice agent. Pricing: see vendor pricing.
Category
Transcription APIs
License
—
Stars
—
Last push
—
Pricing
see vendor pricing
Platforms
Cloud, API
What it is
Ultravox is Fixie.ai's speech-native LLM that consumes audio directly without a separate ASR step, reducing pipeline latency. Fixie also offers a hosted agent runtime that wires Ultravox with TTS providers for end-to-end voice apps. The open weights variant gives developers an OSS path to speech-in LLMs.
Best for: Developers wanting an open speech-native LLM as the brain of their voice agent.
Watch out for: Newer entrant; production tooling less mature than OpenAI Realtime.
Watch out for: Newer entrant; production tooling less mature than OpenAI Realtime.
Features
| Speaker diarization | No |
| Word-level timestamps | No |
| Streaming / real-time | No |
| Languages supported | None |
| HIPAA eligible | No |
Ultravox Agents vs Whipscribe
| Feature | Ultravox Agents | Whipscribe |
|---|---|---|
| Category | Transcription APIs | Transcription APIs |
| Pricing | see vendor pricing | free beta |
| Speaker diarization | — | Yes |
| Word timestamps | — | Yes |
| Streaming | — | No |
| Languages | — | 99 |
| Platforms | Cloud, API | Web, API, MCP |
Alternatives to Ultravox Agents
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.