Use Deepgram when you have your own audio. Use Spoken when you want a published podcast as Markdown. Deepgram's Nova-2 transcribes audio at roughly $0.46 per hour with diarization labels (Speaker 1, Speaker 2). Spoken returns the existing transcript for any podcast episode that has a published one, for $0.08–$0.15 flat, with real speaker names already attached, no audio file required.
Side-by-side comparison
| Deepgram (Nova-2 + diarization) | Spoken | |
|---|---|---|
| Category | Speech-to-text API | Transcript retrieval API |
| Input | Audio file URL or upload | Search query or episode ID |
| Speaker labels | "Speaker 0", "Speaker 1" (diarization) | Real names: "Lex Fridman", "Sam Altman" |
| Cost per podcast hour | ~$0.46/hr + audio handling + LLM pass for naming | $0.08–$0.15 per episode, names included |
| Output format | JSON transcript with word timings | Markdown with speaker bold + timestamps |
| Time to first transcript | Download audio + processing time | Under 30 seconds, single fetch |
| Streaming/real-time | Yes | No (published podcasts only) |
| Works on your own audio | Yes (any file) | No |
| Works on published podcasts | Yes, after you fetch and host the audio | Yes, in one API call |
The hidden cost of using Deepgram for podcasts
Deepgram's listed price is per minute of audio. For published podcasts, the real cost includes everything around that:
- Audio retrieval: locating the .mp3 file, downloading 50–100 MB per episode
- Storage and ingress: your bandwidth and S3 (or equivalent) charges
- Diarization post-processing: "Speaker 0" and "Speaker 1" mean nothing to an LLM, so you need a second pass to work out who is speaking
- Latency: minutes per episode versus seconds with a retrieval API
For a 1-hour podcast, Deepgram's $0.46/hr becomes closer to $1.00+ once you add the surrounding work. Spoken returns the finished output for $0.08–$0.15 per episode.
Where Deepgram wins
Pick Deepgram for
- Your own audio files: meetings, sales calls, internal recordings
- Real-time / streaming transcription
- Custom vocabulary and model fine-tuning
- Voice agents and live captioning
- 45+ language coverage with one provider
Pick Spoken for
- Any published podcast episode as Markdown
- Podcast summarizers, RAG over podcasts, research agents
- You want real speaker names, not diarization labels
- You don't want to host audio or run a pipeline
- Flat per-episode pricing, no per-minute billing
What this looks like in practice
With Deepgram (the pipeline you have to build)
# 1. Find and download the audio file
# 2. Upload to your storage
# 3. Submit to Deepgram with diarization
curl -X POST "https://api.deepgram.com/v1/listen?diarize=true&model=nova-2" \
-H "Authorization: Token YOUR_KEY" \
--data-binary @episode.mp3
# 4. Parse JSON, group by speaker, map "Speaker 0/1" to real names with an LLM
# 5. Format as Markdown for your agentWith Spoken
curl -H "x-api-key: pt_demo" https://spoken.md/transcripts/1000651996090
# Markdown with real names and timestampsFAQ
Is Spoken a Deepgram competitor?
Spoken competes with Deepgram only for the specific use case of getting transcripts of published podcasts. Deepgram is a general speech-to-text platform; Spoken is purpose-built for podcast transcript retrieval. The two are complementary, not equivalent.
Is Spoken cheaper than Deepgram?
For published podcasts, Spoken is typically 5–10x cheaper than Deepgram once you account for audio handling and the LLM pass needed to convert Deepgram's diarization labels into real speaker names. For your own audio, Deepgram is the right tool.
Does Deepgram give real speaker names?
No. Deepgram's diarization outputs "Speaker 0", "Speaker 1", etc. You need to map those to real people using context, usually with another model call. Spoken does this mapping for podcasts as part of the response.
Can I switch between Deepgram and Spoken in the same project?
Yes. Many teams use Spoken for podcasts and Deepgram for user-uploaded audio in the same product. The interfaces are different but neither locks you in.
What does Spoken cost per podcast?
Spoken costs $0.15 per transcript in 100-packs, $0.10 in 500-packs and $0.08 in 2,000-packs. Errors are never charged, Spoken credits never expire, and repeat fetches of the same episode are free.
TL;DR: Deepgram for your own audio. For published podcasts, Spoken: one API call, real speaker names, and 5–10x cheaper per episode.
"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.