Ultravox Agents
Don’t want to wire up the Ultravox Agents API? Drop the file here.
The first 20 minutes of any recording are transcribed free: a recording up to 20 minutes transcribes in full, a longer one is previewed, and a pack from $6 (500 minutes) transcribes the rest and opens every export, and credits never expire.
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.
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.
Watch out for: Newer entrant; production tooling less mature than OpenAI Realtime.
What people actually do with Ultravox Agents-style transcription
The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.
Features
| Speaker diarization | No |
| Word-level timestamps | No |
| Streaming / real-time | No |
| Languages supported | None |
| HIPAA eligible | No |
Links
Ultravox Agents vs Whipscribe
| Feature | Ultravox Agents | Whipscribe |
|---|---|---|
| Category | Transcription APIs | Transcription APIs |
| Pricing | Not verified | $6–$24 one-time packs (credits never expire) · first 20 minutes free |
| Speaker identification | Not verified | Named in the summary, key quotes and chapters |
| Word timestamps | Not verified | Yes |
| Streaming | Not verified | No |
| Languages | — | 99 |
| Platforms | Cloud, API | Web, API, MCP |
Alternatives to Ultravox Agents
Frequently asked about Ultravox Agents
How much does Ultravox Agents cost?
Ultravox Agents does not publish a self-serve price — it is quoted by the vendor on contact. Expect an enterprise-style agreement rather than a card-and-go signup.
Does Ultravox Agents work on Mac, Windows and Linux?
Ultravox Agents runs on Cloud and API. It is not listed for other platforms; check the vendor for anything beyond Cloud and API.
What are the limitations of Ultravox Agents?
Newer entrant; production tooling less mature than OpenAI Realtime.
Who is Ultravox Agents best for?
Developers wanting an open speech-native LLM as the brain of their voice agent.
Is Ultravox Agents open source?
No. Ultravox Agents is a proprietary API from Fixie.ai. If you need source you can read and run yourself, the open-source tools in this directory are the place to look.
Can I use Ultravox Agents in the browser?
No — Ultravox Agents is a Cloud and API application, not a web app. You install it rather than sign in to it.
Where is the Ultravox Agents source code?
On GitHub at github.com/fixie-ai/ultravox. It is maintained by Fixie.ai.
What kind of tool is Ultravox Agents?
In this directory Ultravox Agents is filed under voice agent, voice middleware as a API.
What are the alternatives to Ultravox Agents?
There is a side-by-side page at /tools/ultravox-agents-alternatives comparing Ultravox Agents with the closest tools in the same category on price, platform and features.
Can I automate Ultravox Agents-style transcription without running it myself?
Yes. If what you want is transcripts rather than the tool itself, Whipscribe does the same job as a hosted API: submit a file or URL, poll a job id, pull the result as txt, json, srt, vtt or docx. $0.012 a minute — about $0.72 an audio hour — bought as credits that never expire. The automation recipes on this site show it wired to Drive folders, Zoom recordings, S3 buckets and no-code platforms.
How is Whipscribe different from Ultravox Agents?
Ultravox Agents is another vendor's product; Whipscribe is a per-minute transcription service. Recordings are transcribed on our own servers and never used for training, and every job returns five formats plus an AI summary, quotes and topics. The first 20 minutes of any recording are transcribed free, and a pack from $6 (500 minutes) transcribes the rest and opens every export.
What does transcription cost if I use Whipscribe instead of Ultravox Agents?
$0.012 a minute — about $0.72 an audio hour — bought as credits that never expire. There is no subscription and no monthly minimum: a 3-hour recording is about $2.16, a thousand-hour archive is about $720 once. The first 20 minutes of any recording are transcribed free, and a pack from $6 (500 minutes) transcribes the rest and opens every export, so you can see what your recording holds before paying anything.
Where is the Ultravox Agents category heading?
Three things are moving across the whole speech-to-text market right now: summaries, action items and speaker insights generated on top of the transcript rather than sold separately; private, secured deployment where the audio never leaves a boundary you control; and agent access — transcription exposed as a tool that Claude, Cursor or a workflow runner can call directly. Whipscribe ships all three today: per-job insights, our own servers, and an MCP server.
Whipscribe is a hosted transcription 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.
Transcribe your recordings
Using Ultravox Agents today? Send your next recording here and compare the transcript. Transcribe any language, any recording · Transcription services from $0.29 an hour · Transcribe from any meeting or recording platform · How to transcribe, step by step
Explore
All transcription tools · By language · By platform · By file format · How-to guides · Transcription services · Transcription API · Pricing
Long recording to get through?
One file up to 10 hours, as an upload or a link: see how to transcribe an MP3 of any length, a podcast episode as text from its link and the SRT generator.
Comparing tools before you pay?
If you would rather pay a service than run software yourself: see an honest roundup of the best transcription services, affordable transcription priced per hour and transcription services from $6.