# elevenlabs/elevenlabs-python

The official Python SDK for the ElevenLabs API.

Repository: https://github.com/elevenlabs/elevenlabs-python
Canonical: https://ross.abutalabs.com/products/elevenlabs-python
Homepage: https://elevenlabs.io/docs/api-reference/overview
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, text-to-speech, conversational-ai
Last push: 2026-08-25T21:32:51+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 89
- inputs: {"age_days": 1256, "days_push": 8, "days_rel": 8, "gap_med": 5, "n_releases_24m": 114}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3078, forks 438 (observed 2026-08-28T04:07:41.820506+00:00)

## What it is
The official Python SDK for the ElevenLabs API, providing programmatic access to text-to-speech, speech-to-text, voice cloning, dubbing, music generation, and conversational voice agents. It wraps the full REST and WebSocket API surface with typed clients and streaming support.

## Use cases
- convert text to lifelike speech in Python
- transcribe audio to text with speech recognition
- build a conversational voice agent
- clone a custom voice from audio samples
- dub video content into other languages
- stream low-latency tts audio over websockets
- generate sound effects or music from prompts

## When to choose
- you want to integrate ElevenLabs voice AI into a Python application
- you need official, typed bindings with streaming and websocket support
- you are building voice agents, audiobooks, or dubbing pipelines in Python

## When to avoid
- you use JavaScript/TypeScript instead of Python (use the official Node SDK)
- you need a self-hosted or offline speech synthesis solution
- you don't want to depend on the paid ElevenLabs cloud API

## Facets
- artifact type: library
- maturity: active
- function: sdk, tts, speech-recognition, http-client, audio-processing, agent-framework
- domain: artificial-intelligence, speech-processing, large-language-models
- platform: python, cross-platform
- tags: text-to-speech, voice-cloning, elevenlabs, voice-ai, dubbing, conversational-ai, api-client, audio, ai-agents

## Member repositories
- elevenlabs/elevenlabs-python (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.820506+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:27:52.583213+00:00, confidence not recorded.
  - readme: https://github.com/elevenlabs/elevenlabs-python (fetched 2026-08-28T04:07:41.820506+00:00, sha c5e9263a4f42)
  - homepage: https://elevenlabs.io/docs/api-reference/overview (fetched 2026-08-29T09:43:19.555725+00:00, sha 8d8f03bd521b)
  - site_page: https://elevenlabs.io/docs/eleven-agents/overview (fetched 2026-08-29T09:43:19.565593+00:00, sha bfb2fea3a795)
  - site_page: https://elevenlabs.io/docs/eleven-api/quickstart (fetched 2026-08-29T09:43:19.567148+00:00, sha 6f14bca8ffd1)
  - site_page: https://elevenlabs.io/docs/overview/intro (fetched 2026-08-29T09:43:19.558357+00:00, sha e14c9379ae5b)
  - site_page: https://elevenlabs.io/docs/help-center (fetched 2026-08-29T09:43:19.560440+00:00, sha 53124da8e883)
  - site_page: https://elevenlabs.io/docs/eleven-creative/overview (fetched 2026-08-29T09:43:19.564061+00:00, sha 19f26b91fb35)
  - site_page: https://elevenlabs.io/docs/reception-ai/overview (fetched 2026-08-29T09:43:19.568624+00:00, sha 189febce7e11)
  - site_page: https://elevenlabs.io/docs/changelog (fetched 2026-08-29T09:43:19.570298+00:00, sha 73a2613c0687)
  - site_page: https://elevenlabs.io/pricing/api (fetched 2026-08-29T09:43:19.562241+00:00, sha 5043c31f5265)
- Data as of 2026-08-30T08:39:29.467469+00:00.