Don't Want to Build on AssemblyAI? Get Speaker Labels

AssemblyAI is a transcription API. If you are building a product on it, that is the right tool. If you just need speaker labels from a recording you already have, you do not want an SDK, webhooks, or a developer sprint.

Upload the file. Review who said what. Guest runs are free (2/day). You still rename Speaker 1 and review. This page is for that job.

AssemblyAI is an API; this page is for labels

AssemblyAI is a developer product. You get an API key, write a client, handle webhooks, and parse JSON. That is the right path when transcription is a feature inside software you ship.

It is the wrong path when the job is one recording on your laptop and a labeled transcript you can read.

We are not an AssemblyAI SDK. No SDK. AssemblyAI stays behind Speaker Separation. You do not write webhooks. You upload the file in the browser and get Speaker 1 / Speaker 2 back.

If the file is any multi-speaker recording and you still need who said what: how to split audio by speaker, then rename the labels

What Speaker Separation actually returns

Speaker Separation takes a recording and returns a labeled transcript.

Upload the file. The run labels each voice (Speaker 1, Speaker 2). You rename those labels. You can download isolated stems (one audio file per voice) and export txt or srt.

Guest runs are free (2/day). Signed-in orgs pay 2 credits per minute of audio, rounded up, with a 1-minute floor.

That is the job: who said what on a recording you already have. It is not a certified transcript. It is not a Zoom bot. It is not an SDK.

You still review. Overlaps and wrong labels still need a listen.

Other no-code categories

These are other products. We do not publish their prices. Pick the category that matches the job.

Meeting bots (Otter, Fireflies)

A bot joins Zoom, Meet, or Teams and transcribes the call. Useful when the job is catching the meeting from the calendar. Not useful for a file you already have.

We do not auto-join Zoom.

Upload tools (Rev)

You upload audio and get a transcript back. Some plans add a human review pass. Useful when you want a person to check the machine draft, or when you need a certified copy.

We do not sell that.

Editors (Descript)

You edit the recording by editing the transcript. Useful when the job is cutting a podcast or video. Evaluate that workflow if editing is the job.

If you are still choosing software against a studio demo: choose transcription software for your audio, not the vendor clip

What we do not do

Speaker Separation does not:

• Give you an SDK, API key, or webhooks to write
• Auto-join Zoom, Meet, or Teams
• Return a certified transcript or a court record
• Invent real names (you still rename Speaker 1)
• Beat Otter on price. We do not claim that.

Credit-based. No seat multiplier. Start with 30 free credits. Pack credits never expire. Unused included credits do not carry forward. Paid checkout charges immediately. There is no 7-day trial.

We do not train models on your files.

How to try it

Pick a recording you already have.

1. Upload it to Speaker Separation. Guest runs are free (2/day). No account.
2. Rename Speaker 1 and Speaker 2.
3. Review overlapping turns. Download stems or export txt/srt if you want them.
4. You still review before you share.

Sign in if you want the job kept. Start with 30 free credits. Pack credits never expire. Unused included credits do not carry forward. Paid checkout charges immediately.

Try Speaker Separation →

Frequently asked questions

Do I need an AssemblyAI SDK?

No. Upload the file. AssemblyAI stays behind the tool. You do not write webhooks or stand up an integration. No SDK.

Can I try it without an account?

Yes. Guest runs are free (2/day). Sign in if you want the job kept until you delete it.

What does a signed-in run cost?

2 credits per minute of audio, rounded up, with a 1-minute floor. Start with 30 free credits. Pack credits never expire. Unused included credits do not carry forward. Paid checkout charges immediately. There is no 7-day trial.

Do you join my Zoom call?

No. We do not auto-join Zoom, Meet, or Teams. Export the audio, then upload the file.

Is this a certified transcript?

No. It is a working labeled transcript. You still review. Do not file it as an official record.

Are you cheaper than Otter?

We do not claim that. Otter is a meeting bot with seats. We charge credits per minute of audio you upload. Different products.

---

Need speaker labels without an SDK? Upload a recording. Guest runs are free (2/day). You still review.