IndexTTS
PulseGate's liveness check found it on 3 Oct 2026; it has been in the index since 21 Aug 2026. How this is checked
IndexTTS-2.5 is an open-weight zero-shot text-to-speech model developed by IndexTeam and Bilibili. It generates multilingual speech, transfers a voice across languages from a single reference clip, and provides emotion and speaking-speed controls for developers and researchers.
Inferred · not functionally tested
Overview
6 featuresPurpose: Creating natural multilingual speech and cloning a voice from a single reference recording.
Inferred · not functionally tested
Audience: developers and researchers building speech and voice-cloning applications
Inferred · not functionally tested
Functions: voice_synthesis
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Open Source · platforms: CLI, WEB · deployment: browser, cli, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: huggingface.co. These links do not verify the individual claims.
IndexTTS is a Text to speech project. Inferred · not functionally tested: It focuses on creating natural multilingual speech and cloning a voice from a single reference recording. Inferred · not functionally tested: IndexTTS is an open-source project aimed at developers and researchers building speech and voice-cloning applications. Basis unknown · not verified: IndexTTS is open source under the Open Source license. Basis unknown · not verified: It ships for the web, the command line, and API, and it can be self-hosted.
IndexTeam, Bilibili builds and maintains IndexTTS, and it first shipped in 2025. Development happens publicly on GitHub with 23.3k stars and 65 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include zero-shot voice cloning, multilingual synthesis, and cross-lingual transfer.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Zero-shot voice cloning
- Multilingual synthesis
- Cross-lingual transfer
- Emotion control
- Speaking speed control
- Chinese Pinyin control
Topics: Inferred · not functionally tested
Built with & integrations
- AWS
- x-amz-cf-id header · x-amz-cf-pop header · via header
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed21 Aug · 03:49 UTCBilibili IndexTTS-2.5 seen via Hacker News firehose (Algolia)Source: Hacker News firehose (Algolia) · Open
Frequently asked questions about IndexTTS
- What is IndexTTS?
- Inferred · not functionally tested: IndexTTS focuses on creating natural multilingual speech and cloning a voice from a single reference recording. It is catalogued under Text to speech on PulseGate.
- Who should use IndexTTS?
- Inferred · not functionally tested: IndexTTS is an open-source project built for developers and researchers building speech and voice-cloning applications.
- Does IndexTTS have a free plan?
- Basis unknown · not verified: Yes — IndexTTS is open source under the Open Source license and free to use.
- What platforms does IndexTTS run on?
- Basis unknown · not verified: IndexTTS runs on the web, the command line, and API. It can also be self-hosted.
- Is IndexTTS still maintained?
- PulseGate's liveness check found it on 3 Oct 2026. Its GitHub repository shows 65 commits in the last 90 days.
- Who makes IndexTTS?
- IndexTTS is developed by IndexTeam, Bilibili.
- How long has IndexTTS been around?
- IndexTTS first shipped in 2025.
- Is IndexTTS open source?
- Basis unknown · not verified: Yes — IndexTTS is open source under the Open Source license.
Similar projects
Closest matches by what these projects do