Speech is Cheap is a Google Speech-to-Text alternative for recorded workloads that need a lower bill and less cloud setup. The $20 subscription includes 21,600 base minutes, with direct URL submission and optional sound labels. Use Google Cloud when your application depends on its storage ecosystem, speech adaptation or supported live recognition models.
21,600 Audio Minutes per Month
$20
Speech is Cheap subscription, base transcription
Google estimates use Speech-to-Text V2 standard and discounted dynamic batch pricing, with Chirp 3 on supported single-channel English audio. Dynamic batch trades a lower rate for deferred processing.
Google Cloud Speech-to-Text Pricing ; Google Cloud BatchRecognize API ; Google Cloud Chirp 3 Features and LimitsChoose the cost and workflow that fit your product.
At 100,000 base minutes, Speech is Cheap Subscription costs $92.60. Google V2 standard costs $1,600, while discounted dynamic batch costs $300. The dynamic option is included so you can compare Google’s lower-cost deferred service as well.
Speech is Cheap Pricing ; Google Cloud Speech-to-Text PricingSpeech is Cheap supports recordings up to 1,440 minutes. Chirp 3’s batch guidance recommends 1–60 minutes, with a narrower limit for word timing. Compare the selected model’s boundary before building a workflow around the broader Google batch API limit.
Speech is Cheap Product Facts ; Google Cloud Chirp 3 Features and Limits ; Google Cloud Batch TranscriptionSubmit an accessible recording URL or multipart file to Speech is Cheap. Google V2 batch requires Cloud Storage input and Google Cloud authentication. A direct recording API can simplify an application that does not otherwise use Google Cloud.
Speech is Cheap Job Requests ; Google Cloud Batch TranscriptionEnable Label Audio to classify each segment, including music and silence. Use those labels in JSON or add non-speech cues to SRT and VTT captions from the same job.
Speech is Cheap Job Requests ; Speech is Cheap Job Responses ; Speech is Cheap PricingGive users progress updates while their recorded file is processed. Progress SSE returns chronological transcript segments from the job, so your app can show useful output before the final result.
Speech is Cheap Job RequestsWhen recordings already live in Cloud Storage, Google’s project, region and authentication model can fit the rest of your application. Batch jobs can write their output back to Cloud Storage.
Google Cloud Batch Transcription ; Google Cloud BatchRecognize APIGoogle supports model adaptation for selected models and languages, including phrase hints in Chirp 3. Use those controls when names or specialized terms require an explicit recognition vocabulary.
Google Cloud Speech Model Adaptation ; Google Cloud Chirp 3 Features and LimitsGoogle offers streaming recognition for supported models and languages. Use that service when the application must ingest live speech, and check the streaming feature matrix separately from recorded batch.
Google Cloud Streaming Recognition ; Google Cloud Chirp 3 Features and Limits ; Google Cloud Speech Languages and ModelsCompare base transcription and the add-ons your product needs.
| Audio Volume | Speech is Cheap PAYG | Speech is Cheap Subscription | Google V2 Standard, Chirp 3 | Google V2 Dynamic Batch, Chirp 3 |
|---|---|---|---|---|
| 12,500 minutes | $25.00 | $20.00 | $200.00 | $37.50 |
| 25,000 minutes | $50.00 | $23.15 | $400.00 | $75.00 |
| 50,000 minutes | $100.00 | $46.30 | $800.00 | $150.00 |
| 100,000 minutes | $200.00 | $92.60 | $1,600.00 | $300.00 |
| Audio and Features | Speech is Cheap PAYG | Speech is Cheap Subscription | Google V2 Standard, Chirp 3 | Google V2 Dynamic Batch, Chirp 3 |
|---|---|---|---|---|
| 12,500 minutes + speakers | $50.00 | $32.50 | $200.00 | $37.50 |
| 25,000 minutes + speakers | $100.00 | $48.15 | $400.00 | $75.00 |
| 50,000 minutes + speakers | $200.00 | $96.30 | $800.00 | $150.00 |
| 100,000 minutes + speakers | $400.00 | $192.60 | $1,600.00 | $300.00 |
Choose your volume and add-ons. Each step doubles the audio minutes.
$92.60
per month
$200.00
per month
$1,600.00
per month
$300.00
per month
-- means no verified price for the selected feature combination in the tables and calculator.
Put long recordings, sound labels and progress updates to work in your app.
| Compare | Speech is Cheap | Google Cloud Speech-to-Text |
|---|---|---|
| Audio Input | Recorded audio and video. Progress SSE returns results for an existing recording. Speech is Cheap Job Requests | Synchronous, batch and live recognition APIs. The price comparison selects V2 Chirp 3 standard and dynamic batch. Google Cloud Batch Transcription ; Google Cloud Chirp 3 Features and Limits ; Google Cloud Streaming Recognition |
| File Limits | 0.1 to 1,440 minutes per recording. Direct uploads: under 2 GiB. Speech is Cheap Product Facts | The generic batch API accepts files up to 480 minutes. Chirp 3 has narrower guidance: 1–60 minutes for batch, and up to 20 minutes for word timing. Google Cloud Batch Transcription ; Google Cloud Chirp 3 Features and Limits |
| Languages | 100 supported languages; optional detection per speech segment. Speech is Cheap Product Facts ; Speech is Cheap Job Requests | A broad language and region matrix. Chirp 3 diarization is available for a specific subset; confirm the selected locale rather than assuming every feature supports every language. Google Cloud Speech Languages and Models ; Google Cloud Chirp 3 Features and Limits |
| Outputs | JSON, SRT and VTT. Word timestamps and voice-based speaker labels are paid add-ons. Speech is Cheap Job Responses ; Speech is Cheap Pricing | Structured recognition results and optional SRT/VTT batch output. Chirp 3 documents speaker labels; its word-timestamp support description currently conflicts. Google Cloud BatchRecognize API ; Google Cloud Transcript Output Formats ; Google Cloud Chirp 3 Features and Limits |
| Integration | URL or multipart upload, REST, polling, completion webhooks and progress SSE. Speech is Cheap Job Requests ; Speech is Cheap Job Responses | Cloud Storage input, a project and recognizer resource path, and Google Cloud authentication. Batch returns a long-running operation. Google Cloud Batch Transcription ; Google Cloud BatchRecognize API |
| Audio Labels | Label Audio adds a structured label to each segment, including music and silence. Non-speech sounds appear as caption cues in SRT and VTT. Speech is Cheap Job Requests ; Speech is Cheap Pricing | The selected recognition configuration does not document a matching segment-level music, silence and other sound-label output. Google Cloud Recognition Configuration |
| Progress While Processing | Progress updates and chronological transcript segments over SSE from the same recorded job. Speech is Cheap Job Requests | Batch exposes a long-running operation. Streaming recognition provides incremental live results through a separate request path. Google Cloud BatchRecognize API ; Google Cloud Streaming Recognition |
| Support | Initial email response within one business day for subscribers, three for pay as you go. Resolution time is not guaranteed. Speech is Cheap Service Commitments | Google Cloud documentation and account support. Model, region and feature availability must be checked for the selected project. Google Cloud Chirp 3 Features and Limits ; Google Cloud Speech Languages and Models |
Use public timing data to plan your recording workflow.
Speech is Cheap's public Benchmarks lets you inspect processing times by recording length and selected add-ons, with sample counts. Use those cohorts to evaluate the kind of audio your product processes.
Move from Cloud Storage recognition operations to a recording job with a bearer key. Adapt the result structure and choose a webhook or progress SSE for your app.
| Compare | Google Cloud Speech-to-Text | Speech is Cheap |
|---|---|---|
| Submit | POST recognizers/_:batchRecognize files[].uri: gs://… Google Cloud authenticationGoogle Cloud Batch Transcription ; Google Cloud BatchRecognize API | POST <api|upload>/v2/jobs/ api: JSON input_url upload: multipart input_file Authorization: Bearer KEYSpeech is Cheap Job Requests |
| Speaker Labels | features.diarizationConfig words[].speakerLabel Supported Chirp 3 localesGoogle Cloud Chirp 3 Features and Limits ; Google Cloud Recognition Configuration | can_parse_speakers: true output.segments[].speaker_idSpeech is Cheap Job Requests ; Speech is Cheap Job Responses |
| Word Timing | features.enableWordTimeOffsets Model support needs clarification Word startOffset / endOffsetGoogle Cloud Chirp 3 Features and Limits ; Google Cloud Recognition Configuration | can_parse_words: true output.segments[].words[] start / end in secondsSpeech is Cheap Job Requests ; Speech is Cheap Job Responses |
| Status and Text | Operation: done / error / response Recognition results by input fileGoogle Cloud BatchRecognize API | PENDING / COMPLETED / FAILED CANCELED / UNKNOWN output.segments[].textSpeech is Cheap Job Responses |
| Completion | Poll the long-running operation Read inline or Cloud Storage outputGoogle Cloud BatchRecognize API ; Google Cloud Batch Transcription | Webhook: job output Poll GET /v2/jobs/:id Or monitor progress SSE: can_stream_output: trueSpeech is Cheap Job Requests ; Speech is Cheap Job Responses |
api means https://api.speechischeap.com with JSON input_url. upload means https://upload.speechischeap.com with multipart input_file.
A successful upload always returns an SSE stream with text/event-stream, even with can_stream_output: false. In that mode, the final event contains the asynchronous job response.
curl --request POST \
--url https://api.speechischeap.com/v2/jobs/ \
--header 'Authorization: Bearer KEY' \
--header 'Content-Type: application/json' \
--data '{
"input_url": "https://example.com/recording.mp3",
"webhook_url": "https://your-domain.com/transcription-webhook",
"can_parse_speakers": true,
"can_parse_words": true
}'Example request. Replace the URLs and API key. Both add-ons are billed.
Provide a fetchable URL for an existing private storage object or upload audio directly. A gs:// URI is not a public HTTP recording URL, and Google Cloud credentials do not replace the Speech is Cheap bearer key.
Google Cloud Batch Transcription ; Speech is Cheap Job RequestsMap recognized alternatives and word offsets to output.segments and optional words. Speech is Cheap exposes numeric start and end values in seconds at both levels, with speaker_id on segments.
Google Cloud Recognition Configuration ; Speech is Cheap Job ResponsesChoose a completion webhook or recorded progress SSE instead of building around Google’s operation polling. Validate the parser and selected locale on representative audio; do not assume unsupported feature combinations from a generic configuration field.
Google Cloud BatchRecognize API ; Google Cloud Chirp 3 Features and Limits ; Speech is Cheap Job RequestsReview retention and private mode when saving transcripts. Speech is Cheap results are retrievable by job ID, so treat those IDs as sensitive.
A Production Migration
Metacast
Metacast's result versus its previous, unnamed provider
Podcast Transcription
When Metacast's previous provider stopped completing transcription jobs, its team moved production to Speech is Cheap over a weekend. The new API became its primary transcription engine.
Read the Case Study"It's now our primary transcription engine."
No. Submit an accessible recording URL or upload the file directly with your API key. If the file lives in private cloud storage, make it fetchable for the job or use a direct upload.
Yes. The comparison includes V2 dynamic batch at $0.003 per minute as well as standard transcription and its automatic volume tiers. Dynamic batch can defer processing for up to 24 hours.
Yes. Enable Parse Words and Parse Speakers on the same Speech is Cheap job. The response uses seconds for both segment and word timing. Google’s current Chirp 3 documentation conflicts about word timing, so its affected totals are left unpriced rather than treated as unsupported.
Speech is Cheap supports compatible recordings up to 1,440 minutes. For Google, check both the API and selected model: the generic batch limit is 480 minutes, while Chirp 3 recommends a shorter batch duration and has an additional word-timing limit.
The linked sources support the prices, product boundaries and migration details on this page.
Google dynamic batch can fulfill a request within 24 hours at its discounted rate. Standard batch and live recognition have different execution paths. Compare submit-to-usable-output time on identical files before making a speed claim; a batch deadline, live latency and Speech is Cheap’s observed production timings are different measurements.
Speech is Cheap Benchmarks ; Google Cloud BatchRecognize API ; Google Cloud Streaming RecognitionChecked
Checked
Checked
Checked
Checked
Checked
Checked
Checked
Checked
Checked
Checked
Checked
Checked
Checked
Checked
Select Subscription or PAYG on the pricing page. Check included minutes, overage and add-ons for the workload you compared above.
All prices are in USD. Examples use single-channel, whole-minute files no longer than 10 minutes, with selected features on every file. Audio must meet each model's format and size requirements. These are calculated prices, not a claim of equal accuracy or throughput. Totals are rounded to cents.
Speech is Cheap PAYG costs $0.002 per billed minute. Subscription costs $20 per month for 21,600 base minutes, then $0.000926 per extra minute. Unused included minutes expire each month.
Speech is Cheap rounds every file up to a whole minute for base transcription and all enabled add-ons. Subscription totals include the monthly fee, base overage and add-ons on all enabled-job minutes. Partial-minute files increase its billed minutes.
Parse Speakers adds $0.002 per PAYG minute or $0.001 on subscription. Word-Level Timestamps adds $0.001 per PAYG minute or $0.0005 on subscription. Label Audio adds $0.0002 per PAYG minute or $0.0001 on subscription.
Speech is Cheap PricingGoogle V2 standard tiers are $0.016 per minute for the first 500,000 minutes, $0.01 for the next 500,000, $0.008 for the next 1,000,000, and $0.004 thereafter. Each rate applies only to usage in its tier. Dynamic batch costs $0.003 per minute and can defer processing for up to 24 hours. Billing rounds each request to one-second increments.
Google Cloud Speech-to-Text Pricing ; Google Cloud BatchRecognize APIThese Chirp 3 estimates use a supported English locale with speaker diarization included. Word-timing combinations remain unpriced because the model page describes optional timestamps under an unsupported-features heading. The generic API configuration field does not resolve that conflict.
Google Cloud Chirp 3 Features and Limits ; Google Cloud Recognition Configuration ; Google Cloud Speech Languages and ModelsChirp 3 batch guidance recommends recordings of 1–60 minutes, or up to 20 minutes with word timing. These model-specific limits take precedence over the generic 480-minute batch ceiling. Cloud Storage request charges are additional.
Google Cloud Batch Transcription ; Google Cloud Chirp 3 Features and LimitsThe selected Google recognition configuration does not establish an equivalent structured sound-label output. Separate Google products and custom analysis pipelines are excluded.
Estimates exclude tax, trial credits, negotiated discounts, multichannel charges, storage and network charges, and unselected features. Published automatic volume discounts and explicitly labeled promotions are included where stated. Paid Speech is Cheap API access requires a payment method; the free browser demo requires neither an account nor a card.
Speech is Cheap Pricing See All Speech is Cheap Prices