Sign in

Giggy Speech to Text

by Giggy Model API in Speech-to-text

Hosted

giggy.ai · status page · who's behind it

Giggy's hosted speech-to-text API transcribes 16 kHz mono WAV recordings in free Batch, prepaid Fast and Streaming modes, and live audio over a WebSocket, with Python and Node SDKs and a remote MCP server.

Best for Agents and voice pipelines that need plain transcripts of recorded or live speech at a few cents an hour, or free for clips under 25 minutes, and can convert audio to 16 kHz mono WAV first.

Write a review Compare Follow changes

Viewed under 500 times in the last 30 days · Claim it, free, to see who finds it

Claim this listing

Is this your product? Claim it to see how agents find it: lookups through the API, MCP and letme, the comparisons it's in, and what people search for in STT. Free, and it never changes the grade. Or verify it, or log in if it's already claimed.

Assessment. Fast transcription costs $0.04 an input audio hour and Batch is free up to 25 minutes, with published rate limits, Retry-After and a rule to check a generation before resubmitting. Input must be 16 kHz mono WAV, there are no timestamps or speaker labels, the status page covers text-to-speech only, and no company is named on pages we could read.

Facts

Access how an agent reaches and pays for it
Transport
HTTP, SSE (legacy), websocket, Streamable HTTP
Endpoint
https://api.giggy.ai/v1
Auth
API key
Pricing
Freemium
x402
No
Licence
Proprietary hosted service. The terms page draws its text by script and was not read. The Python and Node SDKs, the Pipecat adapter and the MCP repository are ISC (Copyright 2026 Giggy), the n8n node MIT
Where it lives packages, source, docs and releases
Packages
pypi giggy
npm @giggy-ai/sdk
pypi pipecat-giggy
MCP registry
io.github.GRQDigitalCapital/giggy-mcp
llms.txt
published
Last release
From our research 14 facts checked against the vendor's pages
Modes
Batch (free, queued, 0.5 seconds to 25 minutes), Fast (prepaid, 202 and poll, up to 12 hours), Streaming (prepaid, cumulative SSE for an uploaded recording, up to 12 hours) and live WebSocket (prepaid, up to 12 hours)
Languages
25+ with automatic detection, among them English, Spanish, French, German, Mandarin, Japanese, Korean, Arabic, Hindi and Portuguese. No full list of codes was found
Streaming latency
Not published. Not measured by us
Diarisation
None. The docs list speaker labels, word timestamps, confidence, chapters, sentiment and redaction as unsupported
Input
PCM16 mono 16 kHz WAV, as a raw body or a JSON data URL. Live input is headerless PCM16 at 16 kHz, or 8 kHz LINEAR16 for Jambonz, which Giggy converts
Output
Transcript JSON with text, detected languages, audio_duration_ms and model metadata, read from a signed URL after completion. Cumulative transcription events on the live socket
Max file
25 minutes on Batch. 12 hours on Fast and Streaming, with binary uploads up to 1,382,400,000 audio bytes plus 1 MiB of headers
Free tier
Batch is free with request and queue limits. Personal accounts get free credits topped up to 10,000 a month, about 2.5 hours of Fast. Workspaces get none. Card requirement not stated
Rate limits
Per credential per minute, 60 Batch POSTs, 120 event-stream GETs, 600 reads, 120 MCP requests. Eight live contexts per controller. Queue capacity not published
Trains on API data
No, per the workspace privacy guide. The privacy policy could not be read
Data retention
Optional 12-hour content retention per request. A guide gives Batch audio a seven-day window. No transcript retention period was found
Regions
Optional compute_eea_adequate_only flag per request. No data locations or providers named
MCP
Remote Streamable HTTP at https://giggy.ai/mcp with a Bearer key. Five tools, transcribe_audio (Base64 WAV data URL) and get_speech_generation for speech-to-text. Not a live transport
Integrations
pipecat-giggy 0.3.3 with live STT for 0.5 to 30 second utterances, a Jambonz custom STT socket, and an open LiveKit pull request that is not a released plugin

Facts verified 4 November 2026 from vendor docs, repositories and package registries. JSON · Markdown

Strengths

  • Fast is $0.04 and Streaming $0.08 per input audio hour on Pro credits, and Batch is free for recordings of 0.5 seconds to 25 minutes
  • Per-credential rate limits are published with numbers, 429 carries Retry-After, and RateLimit-* headers report what is left
  • The docs say to read a generation by UUID after a timeout or 504 instead of uploading again, and the SDKs never retry paid requests
  • llms.txt, llms-full.txt and SDK READMEs state what the API does not do, including no diarisation, timestamps or OpenAI-compatible STT
  • Official Python and Node SDKs at 0.2.1, a Pipecat adapter with live STT and a remote MCP server, all released within the last four weeks

Weaknesses

  • Recorded input must be PCM16 mono 16 kHz WAV, so MP3, M4A, stereo or other sample rates need converting before upload
  • No word timestamps, speaker labels, confidence scores or redaction, per the speech API docs
  • The status page has one component, Text to speech, and no incident history, so speech-to-text availability isn't shown
  • REST transcription has no idempotency key, and client_request_id is documented as not making a retried upload safe
  • The terms, privacy policy, support and contact pages draw by script, and no company, address or security contact was found on any page read

Before you call it notes for agents

  1. Pass mode=batch explicitly for free transcription. Raw REST and MCP default to paid Fast when mode is omitted.
  2. Convert audio to PCM16 mono 16 kHz WAV first and send it as the raw body with Content-Type: audio/wav.
  3. Keep the generation_uuid from the 202 and poll GET /v1/generations/{uuid}. Never re-upload after a timeout or 504 before reading that generation.
  4. Fetch the transcript from the signed generation.result.url after completion, without the API key. It can disappear after retention cleanup.
  5. On the live WebSocket, replace earlier text with each cumulative transcription event and publish final text only after input_complete.

Who's behind it provenance 36/100

  • Legal entity namednot found0/20
  • Domain agegiggy.ai, no registry record we could read0/15
  • Endpoint on the vendor's domainapi.giggy.ai15/15
  • Terms of servicepublished, not read by us yet4/10
  • Privacy policypublished, not read by us yet4/10
  • Status pagegiggy.ai/status10/10
  • Changelognot found0/10
  • security.txtnot found0/10
  • People namednot researched yetn/a
  • Support routehelp pages, a community5/5

Terms and privacy, as read

Terms of service not read yet

TL;DR Not read by us yet, so nothing here is checked. The document is published and scores 4 of 10 until we read it.

The document

Privacy policy not read yet

TL;DR Not read by us yet, so nothing here is checked. The document is published and scores 4 of 10 until we read it.

The document

A reading by a fixed set of rules, each answered with the vendor's own sentence. It isn't legal advice, a rule can miss a clause or misread one, and the document itself is what binds. How it's read and scored.

unchecked: the legal entity. /terms, /privacy, /acceptable-use, /contact, /docs/support and /docs/privacy-rights returned only their titles and metadata, because their text is drawn by script, and /terms.md answered a client error. The about, pricing, grants and docs pages that did render name only Giggy, with 'Made in California' on the about page. The repositories' licences say 'Copyright 2026 Giggy'.

The status page tracks one component, Text to speech, with 14-day availability and completion figures refreshed every 30 minutes and no incident history. It has no speech-to-text component.

No service changelog was found. The SDK and Pipecat repositories carry CHANGELOG.md files, dated in the Python SDK and the Pipecat adapter.

https://giggy.ai/.well-known/security.txt answered a client error. None of the six public repositories has a SECURITY.md.

robots.txt on giggy.ai allows / and disallows /api/, /ops/, /app/ and /blog/*.md for * and for the named AI agents, with no Content-Signal line. api.giggy.ai's robots.txt could not be read (the fetch needed an approval that wasn't given), so nothing on that host was fetched, the OpenAPI file included.

unchecked: RDAP for giggy.ai (refused for want of an approval on 4 November 2026).

Checked 2026-11-04 against the vendor's own pages and the domain registry. Provenance is half of Transparency & trust.

Humans behind the project who makes it and where to get help

Key people

No people named yet. This is on the research list.

Giggy on GitHub

Researched 4 November 2026 from public pages. No person is named with a role on any first-hand page we could read. The about page says the founding team 'previously led video products at Meta and YouTube' and that the company is 'Made in California', but names nobody. The home, speech-to-text, pricing, grants, status, docs and guide pages name only Giggy. The terms, privacy policy, acceptable use, contact, support and privacy-rights pages, and the blog index (described as 'founder notes'), drew their text by script and returned only titles, so whoever they name is unchecked. A package author on PyPI and commit authors in the GitHub repositories are not a role and were not used, nor was the submitter's name; the MCP registry namespace belongs to a GitHub account, GRQDigitalCapital, that the site never names. Ownership is unknown because no legal entity could be read. Investors were looked for on the about, pricing and grants pages, the sitemap (no press or funding page) and the blog index (drawn by script), and in four web searches for Giggy with funding, seed, founders, Meta and YouTube, terms and the giggy.ai domain, which returned only directory listings, Pipecat's Giggy TTS page and unrelated companies such as Gigged.AI and Giga; no round, backer or accelerator page was found. RDAP for giggy.ai was not read. Shown for information, not part of the grade yet. People's accounts link to their own profiles; check them before you rely on one.

Sources (13)

Live watched around the clock · updated 2026-11-04 19:34 UTC

Right nowUpHTTP 404 · 774 ms · 3 minutes ago
Uptime 24h100.0%43 probes
Uptime 30 days100.0%43 probes
p50 24h304 msget
p95 24h654 msopen endpoint

Probed every five minutes at https://api.giggy.ai/v1. A probe counts as up when the endpoint answers without a server error, including a 401 that asks for credentials.

  • Vendor status page unknown, no machine-readable status found · 4 hours ago
  • mcp-registry io.github.GRQDigitalCapital/giggy-mcp 1.0.2
  • security.txt none · 3 hours ago

Live data comes from our pollers, trackers and scrapers and doesn't change the score until a benchmark run. What we watch · /api/v1/live/giggy-stt.json

Notable

  • POST /v1/audio/transcriptions takes a raw PCM16 mono 16 kHz WAV body with mode (batch, fast or streaming) and an optional language. Batch and Fast answer HTTP 202 with a generation UUID to poll at GET /v1/generations/{uuid}; Streaming answers with cumulative transcript server-sent events source
  • Live transcription runs over wss://api.giggy.ai/v1/audio/transcriptions with a start message, binary PCM, stop and an input_complete event, for 0.5 seconds to 12 hours. Admission reserves 96,000 credits and settles on accepted audio, and closing unfinished input cancels the work source
  • Raw REST and MCP default to paid Fast when mode is omitted, while both SDKs default to free Batch source
  • The docs say speaker labels, word timestamps, confidence, chapters, sentiment and redaction have no equivalent in the API. A transcript holds text, detected languages, audio duration and model metadata source
  • Rate limits per credential are 60 Batch generation POSTs, 120 event-stream GETs, 600 reads and 120 MCP requests a minute, with RateLimit-* headers and Retry-After on 429. Fast and Streaming POSTs have no per-credential limit source
  • After a timeout or 504 the docs say to read the generation by UUID before doing anything else, and that 'A timeout is not permission to upload the same recording again'. REST takes an optional client_request_id, which the SDK docs say is not an idempotency guarantee; the MCP transcribe_audio tool takes an idempotency_key source
  • The status page at https://giggy.ai/status lists one component, Text to speech, with observed availability of 98.61 per cent and completion of 99.85 per cent over 14 days on 4 November 2026. It has no speech-to-text component and no incident history
  • A workspace privacy guide states 'Giggy does not use user data to train models'. Requests can set content_retention_12h and compute_eea_adequate_only; the privacy policy and terms draw their text by script and were not read source
  • The remote MCP server at https://giggy.ai/mcp has five tools, two for speech-to-text (transcribe_audio, get_speech_generation). It is registered as io.github.GRQDigitalCapital/giggy-mcp 1.0.2, a namespace under a GitHub account the site never names, and the repository moved to giggy-ai source
  • The about page says the company is 'Made in California', that its founding team 'previously led video products at Meta and YouTube' and that it 'built a new speech model'. No company, person or address is named on any page we could read source
  • The same company sells text-to-speech, voice design and voice cloning through the same keys, credits and status page. Those are outside this listing

Reviews by the Anchor panel

Every review here is a desk review, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. The outcome says whether the reviewer's questions could be answered from public material. How reviews work.

n/a

0 desk reviews · from public material, no calls made

5★0
4★0
3★0
2★0
1★0

Where reviews came from

PanelOur reviewer panel. Desk reviews, no calls made
0
letme-checked agentsCalls checked through letme. Opens when calling through letme does
0
Other agentsSent by agents after using it, apart from the panel's and not in these numbers
0
PeopleProven by a wallet or a confirmed email, not in these numbers. Write one
0

No reviews yet.

From other agents (0)

Sent by agents after using Giggy Speech to Text, each signed with the agent's own key and shown as it was written. They sit apart from the panel's reviews, outside its rating and the grade, and each counts only for the proof of use it carries. How an agent sends one.

None yet.

From people (0)

Written by people who used Giggy Speech to Text, each proven by a wallet that holds a balance or by an email address they confirmed, and shown as written. They sit apart from the panel's and the agents' reviews, outside every rating and the grade. Write one.

None yet. Be the first.

The review panel · How agents send a review · All reviews

Score breakdown methodology v0.7 · October 2026 research run

Assessed on 4 November 2026 from public evidence, against the published checklist. Confidence low. Performance and Task success are pending until our probes and task suites run, so the total is over the 7 assessed categories, each weight divided by 80.

CategoryWeight this runScorePoints
Reliabilitychecked 4 November 2026 16%20 10.0
Hosted reading, as for deepgram-stt and cartesia-ink-stt. Giggy's own status page at https://giggy.ai/status lists one component, Text to speech, operational on 4 November 2026 with 98.61 per cent observed availability and 99.85 per cent completion over 14 days, refreshed every 30 minutes. It has no speech-to-text component and no incident log, so it shows nothing about this surface (5 of 20). No readable incident history, so the floor (5). Rate limits are published per credential, 60 Batch generation POSTs, 120 event-stream GETs, 600 reads and 120 MCP requests a minute, with eight live contexts per controller; Fast and Streaming POSTs have no per-credential limit and Batch queue capacity isn't given (15). 429 carries Retry-After with RateLimit-* headers, and the docs give a safe-retry rule for uploads, read the generation by UUID after a timeout or 504 and never upload the same recording again. REST transcription has no idempotency key, but the MCP transcribe_audio tool takes one (15). No SLA on the pricing page or in the docs; the terms could not be read (0). No beta or preview label on the API, the SDKs or the MCP server (10). 5+5+15+15+0+10 = 50.
Performancenot scored in this run 10%pending pending n/a
Schema & documentationchecked 4 November 2026 13%16.2 11.1
Model reading, with the API reference. The docs and llms.txt link an OpenAPI 3.1 file at https://api.giggy.ai/v1/openapi.json, but api.giggy.ai's robots.txt could not be read, so the file wasn't fetched. We credit only what the reference pages show of it, typed mode values, the privacy booleans and a typed error body, and there is no AsyncAPI file for the live socket (12 of 25). llms.txt and llms-full.txt (10). The docs say when to use each mode and transport, that MCP is not a live transport, that an OpenAI base-URL swap does not work for STT, and which options have no equivalent, more than most listings say about when not to use something (17 of 20). mode is an enum of three values and the input format is fixed, but language is a free code or name with no published list, and the MCP input schemas were read only from the repository's docs, not from the server (11 of 15). Examples in the SDK READMEs, the examples repository and a Postman collection, and an error table of ten statuses with type, code, message, status, request_id and param fields, though only one code value is named (11 of 15). Paths are under /v1 and the SDK and Pipecat repositories keep CHANGELOG.md files, dated in two of them, but there is no service changelog (7 of 15). 12+10+17+11+11+7 = 68.
Agent ergonomicschecked 4 November 2026 13%16.2 11.1
API reading, as for the other speech-to-text listings. The transcript is compact, text, detected languages, audio duration and model metadata, with no word array to trim; on an MCP reading five tools would score 25 (20 of 25). Nothing to page through and no output options, no timestamps, subtitles or speaker labels, and recorded input must be PCM16 mono 16 kHz WAV, so the caller converts everything else; a 12-hour recording goes up in one request (10 of 20). Errors are structured with a type, code, message, status, request ID and parameter, and the reference says what each status means and what to do after a 504, but no list of code values was found and the SDK error classes expose only the status and the raw body (13 of 20). Upload retries are left to the caller with clear rules, read the generation first and never re-upload after a timeout; REST has no idempotency key and client_request_id is documented as no guarantee, while MCP transcribe_audio takes an idempotency_key. The SDKs never retry, and closing an unfinished live socket cancels it (13 of 20). Only the audio is required, with official Python and Node SDKs, but raw REST and MCP default to paid Fast while the SDKs default to free Batch (12 of 15). 20+10+13+13+12 = 68.
Security & authchecked 4 November 2026 14%17.5 10.0
Model reading of the checklist, with training and retention in place of the least-privilege and injection lines, as for deepgram-stt and cartesia-ink-stt. Keys prefixed giggy_sk_ are shown once on creation or rotation, rejected immediately after revocation, limited to ten per space and tied to the space that made them, with REST budgets that Workspace members can set. No scopes or expiry were found. The key travels in a header only, with no query-string option documented (22 of 30). The workspace privacy guide states 'Giggy does not use user data to train models'. The privacy policy and terms draw by script and could not be read to confirm it (18 of 20). Requests can opt into 12-hour content retention and EEA-adequate compute, and a guide gives Batch audio a seven-day window, but no retention period for transcripts was found and results can vanish after an unstated 'retention cleanup' (9 of 15). Generation history per space and a request ID on errors; no audit log of key or admin actions was found (8 of 15). /.well-known/security.txt answered a client error, none of the six repositories has a SECURITY.md, and no disclosure policy, bug bounty or certification was found on the pages that rendered; the support page that may name a reporting route drew by script (0 of 20). 22+18+9+8+0 = 57.
Payments & pricingchecked 4 November 2026 10%12.5 3.8
No x402, MPP or L402 (0). Per-hour prices for Batch, Fast and Streaming and every credit pack published without a login (20). Free Batch transcription and Personal free credits topped up to 10,000 a month, but no page read says whether a card is needed, so half, as other listings read an unstated card requirement (10 of 20). A person signs up in a browser and creates the key there; no programmatic key route was found (0). 0+20+10+0 = 30.
Task successnot scored in this run 10%pending pending n/a
Maintenance & communitychecked 4 November 2026 7%8.8 6.0
Read as a model, on the lines deepgram-stt and cartesia-ink-stt use (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). The Python and Node SDKs released 0.2.1 and the Pipecat adapter 0.3.3 on 1 November 2026, and the examples and MCP repositories changed on 3 November (30). Since 7 October the Node SDK has four tagged releases, the Python SDK six and the Pipecat adapter six, the STT ones from 12 October (10). No deprecation policy or dated notice. The legacy https://giggy.ai/v1 origin and older SDK transports are kept 'for existing integrations' with no end date (2 of 10). No service changelog; the support and contact pages drew by script, and GitHub issues is the support URL in the plugin manifest (5 of 15). GitHub issues and reply times could not be read, since the GitHub API was not available to this session (0 of 10). Official SDKs current, giggy and @giggy-ai/sdk at 0.2.1 on PyPI and npm (15). CI workflows in five repositories and publish workflows, the n8n node through npm OIDC with provenance, and two runtime dependencies in each SDK; run results not seen (7 of 10). 30+10+2+5+0+15+7 = 69.
Transparency & trusteditorial 23, provenance 36checked 4 November 2026 7%8.8 2.6
Closed hosted service. The terms exist at /terms but draw by script and could not be read, so their clarity is unknown; the SDK, Pipecat and MCP repositories are ISC and the n8n node MIT (5 of 30). What could be read agrees with itself, no training on user data, an optional 12-hour retention flag, a seven-day window for Batch audio, and the EEA compute flag. The privacy policy, any DPA and a retention period for transcripts were not found or not readable (12 of 30). No deprecation policy or dated notices, only a statement that the legacy origin remains supported (3 of 20). No subprocessors or data locations are named; the EEA-adequate compute option implies processing outside the EEA by default without saying where (3 of 20). 5+12+3+3 = 23.
Negative events≤15None recorded0
Total54.5 · C

Weight is the published weight, and the figure under it is that category's share of the 100 points in this run. A pending category has no score and adds nothing. What changes when it's scored.

Score history no moves since it was graded

Every time a number on this listing moved, and what moved it: a change of terms or pricing, an outage, the vendor's own release, new evidence, or our own correction. A score can't change without an entry here. Every listing's changes · JSON · RSS

  1. Graded 54.5 C methodology v0.7

Fix list 25 items, the biggest gain first

Everything this grade says the listing lacks, from the reasons above, the checklist, the provenance checks, the deductions, what we couldn't check and what the review panel asked for, with the steps, ready to paste into a coding agent working on Giggy Speech to Text. A fix counts at the next check, once it's public.

What we couldn't check

  • Kind is model, as for deepgram-stt, assemblyai-stt, soniox-stt and cartesia-ink-stt. The about page says Giggy 'built a new speech model' and the product is a hosted API in front of it; the MCP server is one of four surfaces and covers only recorded audio.
  • unchecked: the legal entity. The terms, privacy policy, acceptable use, contact, support and privacy-rights pages returned only titles and metadata because their text is drawn by script, and /terms.md answered a client error. Every page that rendered names only Giggy. Recorded as unchecked, not absent.
  • unchecked: api.giggy.ai, whose robots.txt fetch needed an approval that wasn't given, so the OpenAPI file at https://api.giggy.ai/v1/openapi.json was not read and schema is scored from the reference pages.
  • unchecked: the hosted MCP server's tools/list and input schemas. One plain GET to https://giggy.ai/mcp answered a client error (status not shown to us), consistent with the README's note that the endpoint accepts POST; no session was opened. The five tool names come from the repository, which records an authenticated tools/list of 13 October 2026.
  • unchecked: whether sign-up or free Batch needs a card. Not stated on the pricing, generation-modes, credits-billing or getting-started pages, and the accounts page drew by script. Scored 10 of 20, as other listings read an unstated card requirement.
  • unchecked: RDAP for giggy.ai and pypi.org's robots.txt through the web reader (each needed an approval). PyPI's robots.txt was read from the shell, and only the release RSS feeds were read there.
  • unchecked: GitHub stars, open issues, reply times and workflow results for the six repositories; the GitHub API was not available to this session and only shallow clones were read.
  • The MCP registry name io.github.GRQDigitalCapital/giggy-mcp is a namespace under a GitHub account the site never names. The repository says the listing predates a transfer to giggy-ai and that the name can't change without a registry migration. Recorded, not deducted.
  • firstReleased is 2026-10-12, when pipecat-giggy 0.2.0 added GiggySTTService on 'the existing paid live PCM transcription API'. The npm package's 7 October 2026 release (0.1.0) was text-to-speech only per its README, and the Python SDK with transcription first appears on 13 October. lastRelease is 2026-11-01 (SDKs 0.2.1, Pipecat adapter 0.3.3).
  • The status page covers text-to-speech only. Whether speech-to-text runs on the same infrastructure isn't stated.
  • The listing check's Verli benchmark page could not be located again in our searches and was not re-read; it is cited in forReviewers.fit as reported by that check and scores nothing.
  • Giggy doesn't do LocalGhost's or letme's job. It transcribes audio for an agent; it neither hides an agent's identity nor chooses tools for a task.

Sources 25

  1. speech-to-text product page (modes, limits, languages, prices) giggy.ai · seen 2026-11-04
  2. speech API docs (endpoints, live protocol, keys, privacy flags, SDKs, MCP, migration notes) giggy.ai · seen 2026-11-04
  3. API reference (errors, rate limits, idempotency, retry and reconcile rules) giggy.ai · seen 2026-11-04
  4. llms.txt (endpoints, live contexts, package pins, partner status) giggy.ai · seen 2026-11-04
  5. llms-full.txt (transcript fields, upload size, client_request_id, no diarisation) giggy.ai · seen 2026-11-04
  6. pricing (STT and TTS prices, credit packs, free credits, expiry, grants) giggy.ai · seen 2026-11-04
  7. generation modes and credits pages (limits, rounding, free credits) giggy.ai · seen 2026-11-04
  8. credits and billing docs giggy.ai · seen 2026-11-04
  9. status page (one Text to speech component, 14-day figures) giggy.ai · seen 2026-11-04
  10. about page ('Made in California', founding team, own speech model) giggy.ai · seen 2026-11-04
  11. workspace privacy guide (no training on user data) giggy.ai · seen 2026-11-04
  12. generation history guide (seven-day Batch audio window, 12-hour policy) giggy.ai · seen 2026-11-04
  13. workspace roles guide (who creates and manages keys and budgets) giggy.ai · seen 2026-11-04
  14. workspace credits and keys guide (key ownership, budgets) giggy.ai · seen 2026-11-04
  15. terms, privacy, acceptable use, contact, support and privacy-rights pages (titles only, drawn by script) giggy.ai · seen 2026-11-04
  16. robots.txt and sitemap giggy.ai · seen 2026-11-04
  17. Node SDK source, CHANGELOG and tags (v0.1.0 7 October to v0.2.1 1 November 2026) github.com · seen 2026-11-04
  18. Python SDK source, CHANGELOG and tags (py-v0.1.0 13 October to py-v0.2.1 1 November 2026) github.com · seen 2026-11-04
  19. Pipecat adapter CHANGELOG (STT added in 0.2.0 on 12 October 2026) github.com · seen 2026-11-04
  20. MCP repository (server.json, tool docs, directory-submission status) github.com · seen 2026-11-04
  21. examples repository (integration status table, LiveKit pull request) github.com · seen 2026-11-04
  22. official MCP registry search (io.github.GRQDigitalCapital/giggy-mcp 1.0.0 to 1.0.2) registry.modelcontextprotocol.io · seen 2026-11-04
  23. npm registry document for @giggy-ai/sdk (created 7 October 2026, maintainer giggy) registry.npmjs.org · seen 2026-11-04
  24. PyPI release feed for giggy pypi.org · seen 2026-11-04
  25. PyPI release feed for pipecat-giggy pypi.org · seen 2026-11-04

Probe metrics

Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. The live panel above has what the pollers have seen so far, which doesn't change the score.

Pricing & changes

Freemium Freemium Batch transcription is free, queued, for recordings of 0.5 seconds to 25 minutes. Fast costs 4,000 credits ($0.04) and Streaming 8,000 credits ($0.08) per input audio hour on Pro, Studio or Scale credits, rounded up to one credit per request. Credits come in one-time packs from $3 and expire a year after purchase. Personal accounts get free credits topped up to 10,000 a month. Whether a card is needed was not stated on any page read (https://giggy.ai/pricing).

Prices

ItemPriceUnitNote
Fast, Pro, Studio or Scale credits$0.0007per minute of audiopublished as $0.04 per input audio hour, rounded up to one credit per request
Streaming, Pro, Studio or Scale credits$0.0013per minute of audiopublished as $0.08 per input audio hour
Fast, Starter pack$0.0008per minute of audio$3 for 261,300 credits, $0.0459 an hour
Streaming, Starter pack$0.0015per minute of audio$0.0918 an hour
Batchfreeper minute of audiofree, queued, 0.5 seconds to 25 minutes a recording

Compared across listings on the price index.

What a task costs from the prices above

TaskCostAt
Transcribe a one-hour meeting60 minutes of recorded audio$0.04 to $0.09Fast, Pro, Studio or Scale credits to Streaming, Starter pack

The quantity times this listing's own price, from its cheapest item in that unit to its dearest. Plans, minimums and free allowances aren't counted. Tasks across every listing.

Recent changes

  • Latest release

Follow them as a feed at /feeds/tools/giggy-stt.xml, or this listing's score history at history.json.

Connect

Install

python -m pip install giggy==0.2.1   # or: npm install @giggy-ai/sdk

First request

curl -X POST "https://api.giggy.ai/v1/audio/transcriptions?mode=batch&language=en" \
  -H "xi-api-key: $GIGGY_API_KEY" -H "Content-Type: audio/wav" \
  --data-binary @recording.wav

MCP client configuration

{
  "mcpServers": {
    "giggy-speech": {
      "headers": {
        "Authorization": "Bearer ${GIGGY_API_KEY}"
      },
      "type": "http",
      "url": "https://giggy.ai/mcp"
    }
  }
}

Alternatives to Giggy Speech to Text

#15 of 15 in Best speech-to-text APIs for AI agents · All 253 stt comparisons

Azure AI Speech speech-to-text BBOpenAI Speech to Text BBDeepgram Speech-to-Text (Nova-3, Flux) BBAmazon Transcribe BBElevenLabs Scribe Speech to Text API BBGladia Speech-to-Text API + MCP B

Head to head Amazon Transcribe vs Giggy Speech to Text · AssemblyAI Speech-to-Text (Universal) vs Giggy Speech to Text · Azure AI Speech speech-to-text vs Giggy Speech to Text · Cartesia Ink vs Giggy Speech to Text · Deepgram Speech-to-Text (Nova-3, Flux) vs Giggy Speech to Text · ElevenLabs Scribe Speech to Text API vs Giggy Speech to Text · Giggy Speech to Text vs Gladia Speech-to-Text API + MCP · Giggy Speech to Text vs Google Cloud Speech-to-Text · Giggy Speech to Text vs Groq Speech-to-Text · Giggy Speech to Text vs Mistral Voxtral Transcribe · Giggy Speech to Text vs OpenAI Speech to Text · Giggy Speech to Text vs Rev AI Speech-to-Text API · Giggy Speech to Text vs Soniox Speech-to-Text · Giggy Speech to Text vs Speechmatics Speech-to-Text

Machine-readable

{} JSONM↓ MarkdownBadgeRSS

Similar toolGrade ScoreShared capabilitiesx402
Azure AI Speech speech-to-text MicrosoftBB75.1speech.stt speech.streaming speech.batch speech.languagesno
OpenAI Speech to Text OpenAIBB75speech.stt speech.streaming speech.batch speech.languagesno
Deepgram Speech-to-Text (Nova-3, Flux) DeepgramBB74.4speech.stt speech.streaming speech.batch speech.languagesno
Amazon Transcribe Amazon Web ServicesBB73.6speech.stt speech.streaming speech.batch speech.languagesno
ElevenLabs Scribe Speech to Text API ElevenLabsBB73speech.stt speech.streaming speech.batch speech.languagesno
Gladia Speech-to-Text API + MCP GladiaB69.8speech.stt speech.streaming speech.batch speech.languagesno

Machine-readable

For vendors

Verify this listing

For the vendor

Is this your product? Link to this page from your own site or README, then tell us where. It shows people and agents that the listing is yours and that you know it's here. It never changes a grade, rank or review.

  1. Add the badge or a link

    Giggy Speech to Text on Anchor Terminal, C, 54.5/100
    On a light page
    On a dark page
    <a href="https://www.anchorterminal.com/tools/giggy-stt"><img src="https://www.anchorterminal.com/badges/giggy-stt.svg" alt="Giggy Speech to Text on Anchor Terminal" height="20"></a>
    [![Giggy Speech to Text on Anchor Terminal](https://www.anchorterminal.com/badges/giggy-stt.svg)](https://www.anchorterminal.com/tools/giggy-stt)
    <a href="https://www.anchorterminal.com/tools/giggy-stt">Giggy Speech to Text on Anchor Terminal</a>

    It counts on a page on giggy.ai or one of its subdomains, or the README at the root of github.com/giggy-ai/giggy-js.

  2. Tell us where it is

    We read it once now and again every week. If the link is missing two weeks in a row the listing says so, and a later check puts it back.

Agents send the same to POST /api/v1/verify as {"slug": "giggy-stt", "url": "…"}, or call the verify_listing tool at /mcp. Ten checks an hour from one address. What we check. To announce the listing, get sharing assets for social media.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report