gladiaio-sdk
Gladia SDK for Python
Decision gist · record as of 2026-08-14
Yes, if you need to integrate Gladia's speech-to-text service into a Python application. The SDK is actively maintained, has low install friction, and provides both sync and async interfaces for flexibility. License treatment is unclear, so verify the terms before production use. No known security vulnerabilities as of the query date.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Python 3.10+ required.
- Gladia API key must be provided via api_key parameter or GLADIA_API_KEY environment variable.
- Low install friction with a pure Python wheel.
License · maintenance · safety
(unclear)
last release 2026-07-23 (22 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 154,878 downloads/mo, #10,841 on PyPI
Alternatives
Verify before relying
from gladiaio_sdk import GladiaClient
gladia_client = GladiaClient(api_key="your-api-key")
transcription = gladia_client.prerecorded().transcribe(
"audio.mp3",
{"language_config": {"languages": ["en"]}},
)
print(transcription.result.transcription.full_transcript)- Whether the Gladia API key and service are free or require paid subscription
- Supported audio formats beyond the wav/pcm example shown
- Rate limits or quotas on transcription requests
- Latency characteristics for live transcription
What it is and what it does
Gladia SDK is a Python client library for the Gladia speech-to-text service. It provides both synchronous and asynchronous interfaces for transcribing audio—either from pre-recorded files (local paths, file objects, or HTTP URLs) or from live audio streams via WebSocket. The SDK handles authentication via API key, manages file uploads when needed, and polls for job completion on pre-recorded jobs. For live sessions, it establishes WebSocket connections and emits events (partial transcripts, final transcripts, errors, session lifecycle) that your code can listen to and act on.
The package depends on httpx for HTTP requests, websockets for real-time connections, pyee for event handling, and dataclasses-json and marshmallow for request/response serialization. It requires Python 3.10 or later. The API surface includes methods like `transcribe()` for pre-recorded audio, `prerecorded_async()` for async pre-recorded work, and `live()` / `live_async()` for real-time transcription, all accepting configuration for language, diarization, translation, and other audio intelligence features.
Use it for
- Transcribe pre-recorded audio files (MP3, WAV, etc.) with language detection and optional translation
- Build real-time transcription into live applications using WebSocket-based streaming
- Extract speaker identity and turn-taking information via diarization in recorded or live audio
- Redact personally identifiable information from transcripts automatically during processing
- Integrate speech-to-text into async Python applications without blocking the event loop
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need to integrate Gladia's speech-to-text service into a Python application.
The SDK is actively maintained, has low install friction, and provides both sync and async interfaces for flexibility. License treatment is unclear, so verify the terms before production use. No known security vulnerabilities as of the query date.
Install
gladiaio-sdk on PyPI
Before you install
Low install friction with a pure Python wheel. Requires Python 3.10+. Active maintenance with a recent release 22 days ago. Five runtime dependencies (dataclasses-json, httpx, marshmallow, pyee, websockets) are all standard, well-maintained libraries.
Python 3.10+ required. Gladia API key must be provided via api_key parameter or GLADIA_API_KEY environment variable.
Quickstart
from gladiaio_sdk import GladiaClient
gladia_client = GladiaClient(api_key="your-api-key")
transcription = gladia_client.prerecorded().transcribe(
"audio.mp3",
{"language_config": {"languages": ["en"]}},
)
print(transcription.result.transcription.full_transcript)Verify before relying
- Whether the Gladia API key and service are free or require paid subscription
- Supported audio formats beyond the wav/pcm example shown
- Rate limits or quotas on transcription requests
- Latency characteristics for live transcription
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <4,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagesdataclasses-jsonhttpxmarshmallowpyeewebsockets |
| Maintenance | Actively maintained 22 days since the last release |
| First released | |
| Downloads | 154,878 / month, #10,841 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: gladiaio_sdk-1.0.5-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “live transcription Python”
- gladiaio-sdkA Python SDK for the Gladia speech-to-text API, supporting both…
- assemblyaiPython SDK for transcribing and understanding audio using…
- amazon-transcribeStreams audio to Amazon Transcribe and receives real-time…
Give your agent the search over MCP, or paste the wish link into any chat.
More Linguistic packages
Detects and normalizes text encoding from unknown or ambiguous sources, supporting all IANA character sets that Python's core library provides codecs for, with the ability to register custom codecs.
tiktoken is a fast BPE tokenizer that converts text into token sequences compatible with OpenAI models, supporting multiple encoding schemes including o200k_base and model-specific encodings.
Install it if you work with OpenAI APIs or need to understand token boundaries in GPT-family models.
Detects character encoding and language in byte sequences with high accuracy, supporting 99 encodings and returning confidence scores, language tags, and MIME types.
Install it if you need to detect character encoding or language in byte data; the rewrite makes it substantially faster and more accurate than its predecessors.
Converts Unicode text to ASCII by transliterating non-ASCII characters into their closest ASCII equivalents, with no runtime dependencies.
However, if transliteration quality or ongoing maintenance matters, consider unidecode instead despite its GPL-only license.
Lark is a parsing library that builds abstract syntax trees from context-free grammars, supporting multiple parsing algorithms (Earley, LALR(1), CYK) with automatic line and column tracking.
Python bindings to the tree-sitter parsing library, enabling incremental parsing and syntax tree analysis for source code.
See also livekit-plugins-gladia · aws_sdk_transcribe_streaming · amazon-transcribe · assemblyai · livekit-plugins-soniox · deepgram-sdk · rev-ai · cartesia · speechmatics-batch · openai-whisper