AssemblyAI is a speech-to-text API. Spoken is a podcast transcript retrieval API. AssemblyAI Universal transcribes audio at roughly $0.17 per hour with diarization included, but outputs anonymous speaker labels (A, B, C). For published podcasts, Spoken returns the existing transcript with real speaker names (Andrew Huberman, Tim Ferriss) for $0.08–$0.15 flat per episode, with no audio to upload and nothing to post-process.
Side-by-side comparison
| AssemblyAI Universal | Spoken | |
|---|---|---|
| Category | Speech-to-text API | Transcript retrieval API |
| Input | Audio file URL or upload | Search query or episode ID |
| Speaker labels | "A", "B", "C" (97% diarization accuracy) | Real names: "Andrew Huberman", "Tim Ferriss" |
| Cost per podcast hour | ~$0.17/hr + audio handling + LLM pass for naming | $0.08–$0.15 per episode, names included |
| Output format | JSON with utterances + word timings | Markdown with speaker bold + timestamps |
| Bundled features | Sentiment, PII redaction, summarization, topic detection | Just the transcript, optimized for LLM context |
| Works on your own audio | Yes | No |
| Works on published podcasts | Yes, after you fetch and host the audio | Yes, in one API call |
Where AssemblyAI wins
AssemblyAI is a strong choice when you need more than a transcript. The "Speech Understanding" model bundles sentiment analysis, PII detection, summarization, and topic detection in one call, which suits compliance-heavy or analytics-heavy workloads. It also offers excellent diarization quality (a 2.9% speaker count error rate per their published benchmarks).
For raw audio you already own, AssemblyAI is one of the best STT APIs available, especially if you would otherwise be stitching together several analysis passes.
Where Spoken wins
For podcasts that have already been published, the full AssemblyAI pipeline is overkill:
- The transcript already exists, so there is nothing to transcribe.
- "Speaker A" and "Speaker B" still aren't useful to an LLM. A 1-hour podcast typically has 2–4 speakers, and resolving them to real names requires a separate model call after AssemblyAI returns.
- You still have to fetch and host the audio yourself.
Spoken collapses all of that into a single call that returns Markdown with real names already attached.
Pick the right tool
Pick AssemblyAI for
- Your own audio: meetings, calls, recordings, interviews
- Bundled analytics (sentiment, PII, summarization) in the same call
- Compliance use cases needing PII redaction
- Building voice agents or live captioning
- Real-time / streaming transcription
Pick Spoken for
- Published podcast episodes as Markdown
- Podcast summarizers, RAG over podcasts, research agents
- Real speaker names without a second model pass
- Flat per-episode pricing
- You want one call instead of a pipeline
FAQ
Is Spoken cheaper than AssemblyAI?
For published podcasts, Spoken is typically 3–5x cheaper than AssemblyAI once you account for audio handling and the LLM pass needed to map AssemblyAI's "Speaker A/B/C" labels to real names. For your own audio, AssemblyAI is the right choice.
Does AssemblyAI give real speaker names?
No. AssemblyAI's diarization returns labels like "A", "B", "C" with high accuracy (about 97%), but doesn't identify who the speakers are. Spoken does this mapping for podcasts as part of the response.
Can I use both AssemblyAI and Spoken?
Yes. Spoken and AssemblyAI combine well: Spoken for podcasts in your product, AssemblyAI for user-uploaded audio. The two solve different parts of the problem.
What about AssemblyAI's bundled features like sentiment and summarization?
AssemblyAI's bundled sentiment and summarization are useful for raw audio analysis and unnecessary for podcast retrieval. Once you have Spoken's Markdown transcript, you can run sentiment, summarization, or any other analysis with the model of your choice, usually for less than the bundled options.
What format does Spoken return?
Spoken returns clean Markdown, Content-Type: text/markdown; charset=utf-8, with speaker names in bold and timestamps per turn. A typical one-hour episode from Spoken produces 8,000–15,000 tokens.
TL;DR: AssemblyAI is excellent for your own audio, especially with bundled analytics. For published podcasts, Spoken is faster, cheaper, and returns real speaker names with no post-processing.
"I used Spoken to add every My First Million episode to my knowledge base, with a cron to pull new ones. Now I can enjoy the podcast on a run, then chat with Claude about it later — every episode saved and accessible in my Claude sessions."
Thousands of transcripts fetched by developers building summarizers, RAG pipelines, and podcast tools
No signup needed: the key pt_demo works on any endpoint.
$0.10 per transcript. Credits never expire.