Haystack

lokutor-haystack adds two Haystack components: LokutorTextToSpeech and LokutorSpeechToText. Source: lokutor-ai/lokutor-haystack (Apache-2.0).

Install

The package is not on PyPI yet. Until it is:

pip install lokutor-haystack
export LOKUTOR_API_KEY=your_key

The key is a Haystack Secret read from LOKUTOR_API_KEY, so it is never written into a serialized pipeline.

Text to speech

from pathlib import Path
from haystack_integrations.components.audio.lokutor import LokutorTextToSpeech

tts = LokutorTextToSpeech(voice="F1", language="en")
audio = tts.run(text="Hello from Lokutor.")["audio"]  # ByteStream, audio/wav
audio.to_file(Path("hello.wav"))

Calls POST /v1/tts/synthesize. voice is F1-F5, M1-M5 or a clone id; language is an ISO code (pass it for predictable results). run accepts voice and language overrides, and run_async exists. Limits are those of the REST API: 5,000 characters per call, WAV output (16-bit PCM, 44.1 kHz, mono).

Speech to text

from haystack_integrations.components.audio.lokutor import LokutorSpeechToText

stt = LokutorSpeechToText(language="en", diarize=True)
docs = stt.run(sources=["meeting.wav"])["documents"]
print(docs[0].content, docs[0].meta["speakers"])

Calls POST /v1/speech-to-text. sources are file paths or ByteStreams and the output is one Document per source. Lokutor decodes WAV only: convert other formats first. meta carries file_path, language_code, and, with diarize=True, speakers; with include_words=True the per-word timings in words. An unreadable file is logged and skipped; an API error raises RuntimeError with Lokutor’s message.

Pipeline example

from haystack import Pipeline
from haystack.components.writers import DocumentWriter
from haystack.document_stores.in_memory import InMemoryDocumentStore

store = InMemoryDocumentStore()
indexing = Pipeline()
indexing.add_component("stt", LokutorSpeechToText(language="en"))
indexing.add_component("writer", DocumentWriter(document_store=store))
indexing.connect("stt.documents", "writer.documents")
indexing.run({"stt": {"sources": ["call.wav"]}})

What was tested

Unit tests with a mocked HTTP layer on haystack-ai 2.10.0 and 3.4.1, and one live round trip (a short sentence synthesized, then transcribed) against api.lokutor.com. Not run: non-English languages, diarization against the live API, run_async against the live API, or any real-world pipeline beyond the example above.

Get Started

SDK

API Reference

Resources

Install

Text to speech

Speech to text

Pipeline example

What was tested

​Install

​Text to speech

​Speech to text

​Pipeline example

​What was tested

Install

Text to speech

Speech to text

Pipeline example

What was tested