Back: Catalog

Kokoro-FastAPI

Kokoro-FastAPI is a Docker-based FastAPI interface that offers the Kokoro-82M text-voice model. The project offers multi-language support, custom audio pack production, and SSML integration by providing OpenAI compatible audio endpoint. CPU, NVIDIA, AMD and Apple have pre-compiled images for Silicon hardware platforms.

KO

Kokoro-FastAPI

New80

remsky · Voice & Text-to-Speech

STARS5.6K
FORKS937
COMMITS0
CONTRIBUTORS0
VERSIONv0.9.0
UPDATEDtoday
PythonText-to-SpeechFastAPIDockerApache-2.0

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • With OpenAI compatible endpoint, you can perform text voiceover in multiple languages.
  • You can create custom audio packs using Inno Clone-Tuner.
  • You can create word or track-based time-stamped subtitles from text.
User reviews
  • • NeutralGitHub Issue

    Error: Error generating speech: Failed to execute 'endOfStream' on 'MediaSource': The 'updating' attribute is true on on

    “**Describe the bug** Was working great earlier now getting this error: Error generating speech: Failed to execute 'endOfStream' on 'MediaSource': The 'updating' attribute is true on one or more of this MediaSource's SourceBuffers. **Branch / Deployment used** Docker CPU…”

  • ↓ NegativeGitHub Issue

    Integrated WebUI does not support Firefox

    “**Describe the bug** The MIME Type used for audio generation is not supported by Firefox (v134.0.2). Works fine with Chromium based Browsers. **Screenshots or console output** `Error generating speech: MediaSource.addSourceBuffer: Type not supported in MediaSource` **Branch /…”

GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech