Rime Text-to-Speech

uv add "pipecat-ai[rime]"

import os

from pipecat.services.rime.tts import RimeTTSService

tts = RimeTTSService(
    api_key=os.getenv("RIME_API_KEY"),
    settings=RimeTTSService.Settings(
        model="coda",
        voice="luna",
    ),
)

from pipecat.services.rime.tts import RimeTTSService
from pipecat.transcriptions.language import Language

tts = RimeTTSService(
    api_key=os.getenv("RIME_API_KEY"),
    settings=RimeTTSService.Settings(
        voice="cove",
        model="mistv2",
        language=Language.ES,
        speedAlpha=1.2,
        reduceLatency=True,
    ),
)

from pipecat.services.rime.tts_v1 import RimeV1TTSService

tts = RimeV1TTSService(
    api_key=os.getenv("RIME_API_KEY"),
    settings=RimeV1TTSService.Settings(
        voice="luna",
        text_lookahead_tokens=4,
    ),
)

import aiohttp
from pipecat.services.rime.tts import RimeHttpTTSService

async with aiohttp.ClientSession() as session:
    tts = RimeHttpTTSService(
        api_key=os.getenv("RIME_API_KEY"),
        settings=RimeHttpTTSService.Settings(
            model="coda",
            voice="luna",
        ),
        aiohttp_session=session,
    )

# Text transformers for TTS
# This will insert Rime's spell tags around the provided text.
async def spell_out_text(text: str, type: str) -> str:
    return RimeTTSService.SPELL(text)

tts = RimeTTSService(
    api_key=os.getenv("RIME_API_KEY"),
    text_transforms=[
        ("phone_number", spell_out_text),
    ],
)

# Text transformers for TTS
# This will insert a one second pause after questions.
async def pause_after_questions(text: str, type: str) -> str:
    if text.endswith("?"):
        return f"{text}{RimeTTSService.PAUSE_TAG(1.0)}"
    return text

tts = RimeTTSService(
    api_key=os.getenv("RIME_API_KEY"),
    text_transforms=[
        ("sentence", pause_after_questions), # Only apply to sentence aggregations
    ],
)

# Text transformers for TTS
# This puts a phoneme string in place of the word "potato" to define how
# it should be pronounced.
async def maybe_say_potato_all_fancylike(text: str, type: str) -> str:
    if using_fancy_voice:
        return tts.PRONOUNCE(text, "potato", "p0xt1at0o")  # po-TAH-to
    else:
        return tts.PRONOUNCE(text, "potato", "p0xt1et0o")  # po-TAY-to

tts = RimeTTSService(
    api_key=os.getenv("RIME_API_KEY"),
    # Coda doesn't support custom pronunciations
    settings=RimeTTSService.Settings(model="mistv3"),
    text_transforms=[
        ("*", maybe_say_potato_all_fancylike), # Apply to all text
    ],
)

# Text transformers for TTS
# This will make the word slow always be spoken more slowly.
async def slow_down_slow_words(text: str, type: str) -> str:
    return text.replace(
        "slow",
        tts.INLINE_SPEED("slow", speed=0.5)
    )

tts = RimeTTSService(
    api_key=os.getenv("RIME_API_KEY"),
    text_transforms=[
        ("*", slow_down_slow_words), # Apply to all text
    ],
)

@tts.event_handler("on_connected")
async def on_connected(service):
    print("Connected to Rime")