#6464th of 108 in VoiceFor voice, speech and music
elevenlabs-python
Official Python SDK for the ElevenLabs speech, voice and agents API
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.2k
- License
- no license
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
2,922 on 29 Apr 20263,191 on 18 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
ElevenLabs is hiring: 128 open roles
Overview
Python client for the hosted ElevenLabs HTTP API, with sync and async clients. It covers text-to-speech (including streaming), voice search and cloning, and ElevenAgents conversational agents, with helpers to define agent workflows and tools in code. It calls ElevenLabs cloud models and needs an API key; nothing runs locally.
Who it is for: Python developers adding ElevenLabs speech or voice agents to apps
Strengths
- Sync ElevenLabs and async AsyncElevenLabs clients, plus streaming text-to-speech
- Agent workflows and tools defined as chained code, validated by build() and storable as JSON
- @client_tool builds a tool schema from a typed function; check_client_tools() flags schema drift
- Installs with pip install elevenlabs; README has runnable snippets for each feature
Weaknesses
- Requires the hosted ElevenLabs service and an API key; models cannot be self-hosted
- No license detected in the repository metadata
- SDK is generated by Fern, so much of the API surface is generated code
- Changing a shared client tool schema affects already-deployed clients immediately
What it needs
- no GPU
- Needs ElevenLabs API key, ElevenLabs cloud API
- Models: eleven_v4, eleven_v4_turbo, eleven_multilingual_v2, eleven_flash_v2_5, scribe_v2
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Voice
See all 108| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 93 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | meetilyDesktop app that records, transcribes and summarizes meetings locally | 87 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 85 out of 100 |